Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1398 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.6992. Min Act: -0.1700
Data Index: 186399 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.5742. Min Act: -0.1700
Data Index: 5174145 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.5117. Min Act: -0.1700
Data Index: 6211652 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.4492. Min Act: -0.1700
Data Index: 4429021 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.4492. Min Act: -0.1700
Data Index: 121213 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.4492. Min Act: -0.1700
Data Index: 1111602 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3867. Min Act: -0.1700
Data Index: 5378604 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3242. Min Act: -0.1700
Data Index: 8383544 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3867. Min Act: -0.1700
Data Index: 7253173 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3242. Min Act: -0.1700
Data Index: 96377 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3242. Min Act: -0.1700
Data Index: 1337148 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.3242. Min Act: -0.1700
Data Index: 3163548 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 5046289 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 274121 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 1330661 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 8203089 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 6343612 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.1992. Min Act: -0.1700
Data Index: 3858713 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.2617. Min Act: -0.1700
Data Index: 3213905 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6992. Min Range: -8.6992
Max Act: 8.1992. Min Act: -0.1700
Data Index: 4600210 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19