Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3953. Min Range: -6.3953
Max Act: 6.3953. Min Act: -0.1700
Data Index: 1493230 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3953. Min Range: -6.3953
Max Act: 6.0828. Min Act: -0.1700
Data Index: 2280089 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3953. Min Range: -6.3953
Max Act: 6.0203. Min Act: -0.1700
Data Index: 5495007 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3953. Min Range: -6.3953
Max Act: 6.0203. Min Act: -0.1700
Data Index: 7362399 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9890. Min Act: -0.1700
Data Index: 672344 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9578. Min Act: -0.1700
Data Index: 2503502 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3953. Min Range: -6.3953
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2940751 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9578. Min Act: -0.1700
Data Index: 7577114 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9578. Min Act: -0.1700
Data Index: 2157026 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9578. Min Act: -0.1700
Data Index: 267627 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 1202981 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9265. Min Act: -0.1700
Data Index: 8703701 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3859886 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5337139 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8434018 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 328512 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 5142304 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 279028 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.8640. Min Act: -0.1700
Data Index: 8580130 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3953. Min Range: -6.3953
Max Act: 5.9265. Min Act: -0.1700
Data Index: 1459488 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19