Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.7321. Min Act: -0.1700
Data Index: 1516231 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.7321. Min Act: -0.1700
Data Index: 5013985 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.7008. Min Act: -0.1700
Data Index: 7359709 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.6696. Min Act: -0.1700
Data Index: 4028579 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.6696. Min Act: -0.1700
Data Index: 6672985 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6619872 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.6071. Min Act: -0.1700
Data Index: 5718894 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.6071. Min Act: -0.1700
Data Index: 5326738 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.5446. Min Act: -0.1700
Data Index: 429978 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.5133. Min Act: -0.1700
Data Index: 520948 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.5446. Min Act: -0.1700
Data Index: 7476822 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6040063 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6967624 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.4508. Min Act: -0.1700
Data Index: 5880611 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.4508. Min Act: -0.1700
Data Index: 1444089 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.4196. Min Act: -0.1700
Data Index: 5045804 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.3883. Min Act: -0.1700
Data Index: 6220329 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.3571. Min Act: -0.1700
Data Index: 7316871 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.3571. Min Act: -0.1700
Data Index: 4873329 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7321. Min Range: -5.7321
Max Act: 5.3258. Min Act: -0.1700
Data Index: 299520 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19