Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1431 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3114. Min Range: -7.3114
Max Act: 7.3114. Min Act: -0.1700
Data Index: 2112373 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3114. Min Range: -7.3114
Max Act: 7.2489. Min Act: -0.1700
Data Index: 2388430 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3114. Min Range: -7.3114
Max Act: 7.0614. Min Act: -0.1700
Data Index: 6377848 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3114. Min Range: -7.3114
Max Act: 7.0614. Min Act: -0.1700
Data Index: 5562752 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9989. Min Act: -0.1700
Data Index: 7948893 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3114. Min Range: -7.3114
Max Act: 7.0302. Min Act: -0.1700
Data Index: 3250029 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9677. Min Act: -0.1700
Data Index: 1921718 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9364. Min Act: -0.1700
Data Index: 7155260 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9677. Min Act: -0.1700
Data Index: 1386649 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9052. Min Act: -0.1700
Data Index: 505063 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.9052. Min Act: -0.1700
Data Index: 6228555 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8739. Min Act: -0.1700
Data Index: 3913727 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8739. Min Act: -0.1700
Data Index: 4232262 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8427. Min Act: -0.1700
Data Index: 3782737 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8427. Min Act: -0.1700
Data Index: 8181001 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8114. Min Act: -0.1700
Data Index: 3345476 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.8427. Min Act: -0.1700
Data Index: 5864389 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.7489. Min Act: -0.1700
Data Index: 7337505 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.7802. Min Act: -0.1700
Data Index: 4232263 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3114. Min Range: -7.3114
Max Act: 6.7489. Min Act: -0.1700
Data Index: 1590496 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19