Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1117. Min Range: -4.1117
Max Act: 4.1117. Min Act: -0.1700
Data Index: 8510617 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.9242. Min Act: -0.1700
Data Index: 3755779 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8929. Min Act: -0.1700
Data Index: 6450003 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8460. Min Act: -0.1700
Data Index: 5518975 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8460. Min Act: -0.1700
Data Index: 1404125 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8147. Min Act: -0.1700
Data Index: 5631207 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8304. Min Act: -0.1700
Data Index: 790860 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.8147. Min Act: -0.1700
Data Index: 8412745 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7834. Min Act: -0.1700
Data Index: 6455565 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7678. Min Act: -0.1700
Data Index: 3436339 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7365. Min Act: -0.1700
Data Index: 3111630 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7522. Min Act: -0.1700
Data Index: 8485473 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7522. Min Act: -0.1700
Data Index: 5346261 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7522. Min Act: -0.1700
Data Index: 2565669 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7365. Min Act: -0.1700
Data Index: 3988942 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7365. Min Act: -0.1700
Data Index: 7977019 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7365. Min Act: -0.1700
Data Index: 3639879 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7209. Min Act: -0.1700
Data Index: 8009157 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.7209. Min Act: -0.1700
Data Index: 5453452 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1117. Min Range: -4.1117
Max Act: 3.6896. Min Act: -0.1700
Data Index: 2197761 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19