Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.9728. Min Act: -0.1700
Data Index: 7387128 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.8165. Min Act: -0.1700
Data Index: 7155123 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.6290. Min Act: -0.1700
Data Index: 346051 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.5978. Min Act: -0.1700
Data Index: 419485 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.5978. Min Act: -0.1700
Data Index: 3836654 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.5978. Min Act: -0.1700
Data Index: 918732 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.5353. Min Act: -0.1700
Data Index: 7541316 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.5040. Min Act: -0.1700
Data Index: 5339905 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.4415. Min Act: -0.1700
Data Index: 8288445 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.4103. Min Act: -0.1700
Data Index: 3203616 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 266506 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3790. Min Act: -0.1700
Data Index: 2374711 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3790. Min Act: -0.1700
Data Index: 7008700 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.2853. Min Act: -0.1700
Data Index: 2601776 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 5885195 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3165. Min Act: -0.1700
Data Index: 6102909 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 6676073 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 8072880 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3165. Min Act: -0.1700
Data Index: 4855523 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9728. Min Range: -7.9728
Max Act: 7.3165. Min Act: -0.1700
Data Index: 875583 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19