Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.6971. Min Act: -0.1700
Data Index: 1589163 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.5721. Min Act: -0.1700
Data Index: 6821643 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.3221. Min Act: -0.1700
Data Index: 8523530 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.3221. Min Act: -0.1700
Data Index: 3081178 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.3221. Min Act: -0.1700
Data Index: 861985 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.3221. Min Act: -0.1700
Data Index: 4398590 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.1971. Min Act: -0.1700
Data Index: 6302790 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.2596. Min Act: -0.1700
Data Index: 7185039 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.1971. Min Act: -0.1700
Data Index: 8499367 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.1971. Min Act: -0.1700
Data Index: 3498312 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.1346. Min Act: -0.1700
Data Index: 8351944 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.0721. Min Act: -0.1700
Data Index: 5427791 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.0721. Min Act: -0.1700
Data Index: 1595353 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.0408. Min Act: -0.1700
Data Index: 7735591 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.0408. Min Act: -0.1700
Data Index: 8494281 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6971. Min Range: -8.6971
Max Act: 8.0096. Min Act: -0.1700
Data Index: 3580271 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6971. Min Range: -8.6971
Max Act: 7.9783. Min Act: -0.1700
Data Index: 417527 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6971. Min Range: -8.6971
Max Act: 7.9471. Min Act: -0.1700
Data Index: 3467301 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6971. Min Range: -8.6971
Max Act: 7.9471. Min Act: -0.1700
Data Index: 6282182 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6971. Min Range: -8.6971
Max Act: 7.9471. Min Act: -0.1700
Data Index: 386775 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19