Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1884 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.8176. Min Act: -0.1700
Data Index: 274993 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1229498 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2033630 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.5676. Min Act: -0.1700
Data Index: 3057259 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.5989. Min Act: -0.1700
Data Index: 8102061 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.5676. Min Act: -0.1700
Data Index: 7583885 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.5364. Min Act: -0.1700
Data Index: 5768116 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4426. Min Act: -0.1700
Data Index: 6299410 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4114. Min Act: -0.1700
Data Index: 2674683 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4114. Min Act: -0.1700
Data Index: 2617866 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3801. Min Act: -0.1700
Data Index: 7571927 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4114. Min Act: -0.1700
Data Index: 723052 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4426. Min Act: -0.1700
Data Index: 3136204 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3801. Min Act: -0.1700
Data Index: 3255366 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3489. Min Act: -0.1700
Data Index: 4149901 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3801. Min Act: -0.1700
Data Index: 7775090 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3801. Min Act: -0.1700
Data Index: 6717666 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.4114. Min Act: -0.1700
Data Index: 2774240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3489. Min Act: -0.1700
Data Index: 1478048 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8176. Min Range: -5.8176
Max Act: 5.3489. Min Act: -0.1700
Data Index: 6063692 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19