Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.9246. Min Act: -0.1700
Data Index: 1959101 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.7996. Min Act: -0.1700
Data Index: 1959104 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.7371. Min Act: -0.1700
Data Index: 2076829 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.7371. Min Act: -0.1700
Data Index: 5120045 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.7371. Min Act: -0.1700
Data Index: 451196 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.6121. Min Act: -0.1700
Data Index: 451190 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.5496. Min Act: -0.1700
Data Index: 2076827 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.4871. Min Act: -0.1700
Data Index: 6535978 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.4871. Min Act: -0.1700
Data Index: 2076826 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.4871. Min Act: -0.1700
Data Index: 7888196 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.4246. Min Act: -0.1700
Data Index: 6535980 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.4246. Min Act: -0.1700
Data Index: 1382917 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.3933. Min Act: -0.1700
Data Index: 1336746 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.3621. Min Act: -0.1700
Data Index: 3543765 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.3621. Min Act: -0.1700
Data Index: 2076830 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.2996. Min Act: -0.1700
Data Index: 4784652 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.2996. Min Act: -0.1700
Data Index: 6535979 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.2996. Min Act: -0.1700
Data Index: 450613 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.2683. Min Act: -0.1700
Data Index: 451197 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9246. Min Range: -6.9246
Max Act: 6.2996. Min Act: -0.1700
Data Index: 4784653 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19