Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.7992. Min Act: -0.1700
Data Index: 6056518 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.6117. Min Act: -0.1700
Data Index: 64312 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.5804. Min Act: -0.1700
Data Index: 7023479 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.4242. Min Act: -0.1700
Data Index: 6673276 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.3929. Min Act: -0.1700
Data Index: 7926213 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.4242. Min Act: -0.1700
Data Index: 1100574 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.3929. Min Act: -0.1700
Data Index: 6952614 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.2992. Min Act: -0.1700
Data Index: 6555190 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.2992. Min Act: -0.1700
Data Index: 3135387 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.2367. Min Act: -0.1700
Data Index: 8706443 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.2054. Min Act: -0.1700
Data Index: 3548162 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1742. Min Act: -0.1700
Data Index: 5112705 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1429. Min Act: -0.1700
Data Index: 1282606 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1429. Min Act: -0.1700
Data Index: 7519481 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 8724760 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 1318453 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 8654469 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 3483075 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 3385285 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7992. Min Range: -6.7992
Max Act: 6.1117. Min Act: -0.1700
Data Index: 8067040 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19