Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.3052. Min Act: -0.1686
Data Index: 339659 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.0239. Min Act: -0.1700
Data Index: 723508 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.6177. Min Act: -0.1699
Data Index: 7093843 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.2739. Min Act: -0.1700
Data Index: 5837114 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.2427. Min Act: -0.1700
Data Index: 7382526 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.1489. Min Act: -0.1700
Data Index: 864904 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.2427. Min Act: -0.1700
Data Index: 5639881 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3677. Min Range: -6.3677
Max Act: 4.7114. Min Act: -0.1700
Data Index: 6466418 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.9927. Min Act: -0.1700
Data Index: 269864 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.0552. Min Act: -0.1700
Data Index: 1202134 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.9927. Min Act: -0.1700
Data Index: 4977949 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.9927. Min Act: -0.1696
Data Index: 5831590 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.3052. Min Act: -0.1700
Data Index: 2522431 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.3677. Min Act: -0.1700
Data Index: 3008945 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.9302. Min Act: -0.1700
Data Index: 6795562 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.8052. Min Act: -0.1678
Data Index: 5639880 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.8364. Min Act: -0.1700
Data Index: 3359219 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.9302. Min Act: -0.1700
Data Index: 7609336 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3677. Min Range: -6.3677
Max Act: 5.7114. Min Act: -0.1700
Data Index: 8510692 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3677. Min Range: -6.3677
Max Act: 6.2114. Min Act: -0.1700
Data Index: 5885863 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19