Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4274. Min Range: -6.4274
Max Act: 6.4274. Min Act: -0.1700
Data Index: 7103983 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4274. Min Range: -6.4274
Max Act: 6.2087. Min Act: -0.1700
Data Index: 1324803 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4274. Min Range: -6.4274
Max Act: 6.1149. Min Act: -0.1700
Data Index: 8690447 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4274. Min Range: -6.4274
Max Act: 6.0524. Min Act: -0.1700
Data Index: 2734385 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.9899. Min Act: -0.1700
Data Index: 3586827 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.9899. Min Act: -0.1700
Data Index: 286818 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.9587. Min Act: -0.1700
Data Index: 1260969 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.9274. Min Act: -0.1700
Data Index: 7291817 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.9274. Min Act: -0.1700
Data Index: 3239033 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8962. Min Act: -0.1700
Data Index: 1304260 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8962. Min Act: -0.1700
Data Index: 1329941 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8649. Min Act: -0.1700
Data Index: 59680 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8649. Min Act: -0.1700
Data Index: 8574819 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 3281439 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 3555863 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 4656280 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8337. Min Act: -0.1700
Data Index: 7817961 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8337. Min Act: -0.1700
Data Index: 4329099 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 8544656 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4274. Min Range: -6.4274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 3990289 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19