Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.3114. Min Act: -0.1700
Data Index: 989162 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2802. Min Act: -0.1700
Data Index: 620535 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 8651155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 3542076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 82918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2177. Min Act: -0.1700
Data Index: 841399 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 8210972 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.2177. Min Act: -0.1700
Data Index: 4442494 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 2447661 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 7848869 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 5585123 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1552. Min Act: -0.1700
Data Index: 8276686 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1239. Min Act: -0.1700
Data Index: 430216 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1552. Min Act: -0.1700
Data Index: 6312809 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1552. Min Act: -0.1700
Data Index: 1467039 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1552. Min Act: -0.1700
Data Index: 3282682 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1552. Min Act: -0.1700
Data Index: 1694261 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1239. Min Act: -0.1700
Data Index: 6355767 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1239. Min Act: -0.1700
Data Index: 4138230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3114. Min Range: -5.3114
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3245812 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19