Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0979. Min Range: -6.0979
Max Act: 6.0979. Min Act: -0.1700
Data Index: 8756103 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0979. Min Range: -6.0979
Max Act: 6.0354. Min Act: -0.1700
Data Index: 2212078 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0979. Min Range: -6.0979
Max Act: 6.0042. Min Act: -0.1700
Data Index: 7383230 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.9104. Min Act: -0.1700
Data Index: 7449146 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.8479. Min Act: -0.1700
Data Index: 7655600 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.8479. Min Act: -0.1700
Data Index: 4003986 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.8167. Min Act: -0.1700
Data Index: 5591668 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.8167. Min Act: -0.1700
Data Index: 2212079 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7854. Min Act: -0.1700
Data Index: 4270575 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7854. Min Act: -0.1700
Data Index: 4815051 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7854. Min Act: -0.1700
Data Index: 967634 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7854. Min Act: -0.1700
Data Index: 2821905 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7542. Min Act: -0.1700
Data Index: 7094267 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6010494 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7542. Min Act: -0.1700
Data Index: 267080 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7229. Min Act: -0.1700
Data Index: 5741242 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.7229. Min Act: -0.1700
Data Index: 8722589 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.6917. Min Act: -0.1700
Data Index: 7094268 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.6917. Min Act: -0.1700
Data Index: 2959724 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0979. Min Range: -6.0979
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1296838 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19