Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3873 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3159. Min Range: -7.3159
Max Act: 7.3159. Min Act: -0.1700
Data Index: 2128926 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3159. Min Range: -7.3159
Max Act: 7.1909. Min Act: -0.1700
Data Index: 2695 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3159. Min Range: -7.3159
Max Act: 7.1284. Min Act: -0.1700
Data Index: 5374 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3159. Min Range: -7.3159
Max Act: 7.0659. Min Act: -0.1700
Data Index: 7116263 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.9409. Min Act: -0.1700
Data Index: 6570042 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.9722. Min Act: -0.1700
Data Index: 6317066 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.9097. Min Act: -0.1700
Data Index: 8126800 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.8472. Min Act: -0.1700
Data Index: 5842347 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.8784. Min Act: -0.1700
Data Index: 2121551 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.8159. Min Act: -0.1700
Data Index: 4514719 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.8159. Min Act: -0.1700
Data Index: 3158972 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.7534. Min Act: -0.1700
Data Index: 2331958 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.7534. Min Act: -0.1700
Data Index: 5669726 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.6597. Min Act: -0.1700
Data Index: 8623868 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.6597. Min Act: -0.1700
Data Index: 1355011 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.6597. Min Act: -0.1700
Data Index: 2008787 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.6597. Min Act: -0.1700
Data Index: 7603269 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.6597. Min Act: -0.1700
Data Index: 8593580 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.5972. Min Act: -0.1700
Data Index: 3939028 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3159. Min Range: -7.3159
Max Act: 6.5972. Min Act: -0.1700
Data Index: 3614285 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19