Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.7241. Min Act: -0.1700
Data Index: 1353508 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.7241. Min Act: -0.1700
Data Index: 852476 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.4116. Min Act: -0.1700
Data Index: 4868713 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.4116. Min Act: -0.1700
Data Index: 5570972 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.3804. Min Act: -0.1700
Data Index: 7307573 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.4116. Min Act: -0.1700
Data Index: 3973745 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.4116. Min Act: -0.1700
Data Index: 2593418 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.3491. Min Act: -0.1700
Data Index: 1473290 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.3491. Min Act: -0.1700
Data Index: 2451749 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.3179. Min Act: -0.1700
Data Index: 2567773 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2866. Min Act: -0.1700
Data Index: 8096899 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2554. Min Act: -0.1700
Data Index: 1629992 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2866. Min Act: -0.1700
Data Index: 3753357 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2554. Min Act: -0.1700
Data Index: 3402836 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3968095 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2554. Min Act: -0.1700
Data Index: 4014735 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2554. Min Act: -0.1700
Data Index: 2359548 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.1929. Min Act: -0.1700
Data Index: 4837319 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3500633 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.2241. Min Act: -0.1700
Data Index: 4578378 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19