Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0966. Min Act: -0.1700
Data Index: 7184261 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 8634872 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 212716 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 4155684 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 7816252 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 4157834 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 8803056 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 2064559 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 3831123 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0966. Min Range: -7.0966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 985958 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 1216576 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 1441165 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 6157336 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 5277728 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 3973432 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9403. Min Act: -0.1700
Data Index: 6539005 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9403. Min Act: -0.1700
Data Index: 4095960 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9091. Min Act: -0.1700
Data Index: 3407642 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9091. Min Act: -0.1700
Data Index: 1721512 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0966. Min Range: -7.0966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 3332596 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19