Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.0108. Min Range: -10.0108
Max Act: 10.0108. Min Act: -0.1700
Data Index: 7301192 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.8858. Min Act: -0.1700
Data Index: 2849996 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.8233. Min Act: -0.1700
Data Index: 8778365 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.7608. Min Act: -0.1700
Data Index: 4263139 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.7608. Min Act: -0.1700
Data Index: 2066221 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.6358. Min Act: -0.1700
Data Index: 548845 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 6570820 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.6358. Min Act: -0.1700
Data Index: 8098526 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 6168146 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 3756801 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 5071204 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 2679689 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.4483. Min Act: -0.1700
Data Index: 5632227 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5108. Min Act: -0.1700
Data Index: 6398450 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5733. Min Act: -0.1700
Data Index: 67027 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.4483. Min Act: -0.1700
Data Index: 7889511 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.5108. Min Act: -0.1700
Data Index: 1301141 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.4483. Min Act: -0.1700
Data Index: 35864 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.3233. Min Act: -0.1700
Data Index: 4139814 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0108. Min Range: -10.0108
Max Act: 9.3858. Min Act: -0.1700
Data Index: 3919599 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19