Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0205. Min Range: -7.0205
Max Act: 7.0205. Min Act: -0.1700
Data Index: 927809 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.8330. Min Act: -0.1700
Data Index: 7661042 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.8330. Min Act: -0.1700
Data Index: 4081686 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.7705. Min Act: -0.1700
Data Index: 8081072 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.7705. Min Act: -0.1700
Data Index: 4809144 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.6767. Min Act: -0.1700
Data Index: 43037 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.6142. Min Act: -0.1700
Data Index: 6212606 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.5517. Min Act: -0.1700
Data Index: 4359974 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.5517. Min Act: -0.1700
Data Index: 2714120 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.4580. Min Act: -0.1700
Data Index: 4022832 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.4267. Min Act: -0.1700
Data Index: 5361588 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.4267. Min Act: -0.1700
Data Index: 5455501 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.3642. Min Act: -0.1700
Data Index: 4875273 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.3642. Min Act: -0.1700
Data Index: 8375837 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.3642. Min Act: -0.1700
Data Index: 7179913 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.3330. Min Act: -0.1700
Data Index: 8693576 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.3330. Min Act: -0.1700
Data Index: 5787773 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.2705. Min Act: -0.1700
Data Index: 2578274 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3234649 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0205. Min Range: -7.0205
Max Act: 6.2705. Min Act: -0.1700
Data Index: 6065718 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19