Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.7861. Min Act: -0.1700
Data Index: 2975379 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6922. Min Act: -0.1700
Data Index: 6828990 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6609. Min Act: -0.1700
Data Index: 1225164 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6609. Min Act: -0.1700
Data Index: 457541 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5983. Min Act: -0.1700
Data Index: 1425979 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5983. Min Act: -0.1700
Data Index: 5419803 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5670. Min Act: -0.1700
Data Index: 5928160 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5827. Min Act: -0.1700
Data Index: 3100288 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5983. Min Act: -0.1700
Data Index: 7649833 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5827. Min Act: -0.1700
Data Index: 777795 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5514. Min Act: -0.1700
Data Index: 1386182 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5357. Min Act: -0.1700
Data Index: 5768484 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5044. Min Act: -0.1700
Data Index: 2822608 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5642870 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5044. Min Act: -0.1700
Data Index: 801329 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5505479 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4731. Min Act: -0.1700
Data Index: 6720803 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4574. Min Act: -0.1700
Data Index: 1741389 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4731. Min Act: -0.1700
Data Index: 4120735 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4417. Min Act: -0.1700
Data Index: 2500469 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19