Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4177. Min Range: -8.4177
Max Act: 8.4177. Min Act: -0.1700
Data Index: 987191 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4177. Min Range: -8.4177
Max Act: 8.1677. Min Act: -0.1700
Data Index: 8729268 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.9489. Min Act: -0.1700
Data Index: 6690136 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.8864. Min Act: -0.1700
Data Index: 7494080 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.7614. Min Act: -0.1700
Data Index: 4924825 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.5739. Min Act: -0.1700
Data Index: 4223744 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.5427. Min Act: -0.1700
Data Index: 8253783 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.4489. Min Act: -0.1700
Data Index: 8574336 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.3552. Min Act: -0.1700
Data Index: 1952843 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.4177. Min Act: -0.1700
Data Index: 8018071 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.3552. Min Act: -0.1700
Data Index: 401783 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.3552. Min Act: -0.1700
Data Index: 1308317 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.2614. Min Act: -0.1700
Data Index: 6273478 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.2302. Min Act: -0.1700
Data Index: 8037548 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.1364. Min Act: -0.1700
Data Index: 4275773 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.2302. Min Act: -0.1700
Data Index: 7218770 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.1052. Min Act: -0.1700
Data Index: 4054332 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.1364. Min Act: -0.1700
Data Index: 6125578 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4177. Min Range: -8.4177
Max Act: 7.1677. Min Act: -0.1700
Data Index: 968935 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4177. Min Range: -8.4177
Max Act: 6.9802. Min Act: -0.1700
Data Index: 1603879 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19