Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.5848. Min Act: -0.1700
Data Index: 3486838 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.4598. Min Act: -0.1700
Data Index: 1047958 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.2098. Min Act: -0.1700
Data Index: 8438106 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.2723. Min Act: -0.1700
Data Index: 2401604 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.2098. Min Act: -0.1700
Data Index: 4373563 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.1473. Min Act: -0.1700
Data Index: 5919899 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.1473. Min Act: -0.1700
Data Index: 7887400 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.0848. Min Act: -0.1700
Data Index: 688591 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.0848. Min Act: -0.1700
Data Index: 5520072 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.0223. Min Act: -0.1700
Data Index: 8402965 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5848. Min Range: -8.5848
Max Act: 8.0223. Min Act: -0.1700
Data Index: 8479031 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.8973. Min Act: -0.1700
Data Index: 5846062 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.9598. Min Act: -0.1700
Data Index: 2512887 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.9598. Min Act: -0.1700
Data Index: 634693 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.8973. Min Act: -0.1700
Data Index: 737350 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.9598. Min Act: -0.1700
Data Index: 2159085 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.8348. Min Act: -0.1700
Data Index: 6858612 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.8348. Min Act: -0.1700
Data Index: 2474165 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.7723. Min Act: -0.1700
Data Index: 5838883 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5848. Min Range: -8.5848
Max Act: 7.7098. Min Act: -0.1700
Data Index: 1544865 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19