Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.6928. Min Act: -0.1700
Data Index: 5734681 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.6928. Min Act: -0.1700
Data Index: 7701322 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.6928. Min Act: -0.1700
Data Index: 7699337 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.6928. Min Act: -0.1700
Data Index: 7322457 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.5678. Min Act: -0.1700
Data Index: 4605213 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.5678. Min Act: -0.1700
Data Index: 5555930 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.5678. Min Act: -0.1700
Data Index: 2493159 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.5678. Min Act: -0.1700
Data Index: 7471763 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.5678. Min Act: -0.1700
Data Index: 5961445 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 5402339 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 256559 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 4353537 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 1273289 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 1636701 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.4428. Min Act: -0.1700
Data Index: 5912547 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.3178. Min Act: -0.1700
Data Index: 5579688 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.3178. Min Act: -0.1700
Data Index: 1636661 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.3178. Min Act: -0.1700
Data Index: 5718061 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.3178. Min Act: -0.1700
Data Index: 5871223 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.6928. Min Range: -18.6928
Max Act: 18.3178. Min Act: -0.1700
Data Index: 1649807 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19