Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.7242. Min Act: -0.1679
Data Index: 8432247 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6634. Min Act: -0.1700
Data Index: 2395510 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6373. Min Act: -0.1698
Data Index: 7271197 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6199. Min Act: -0.1699
Data Index: 2742349 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6199. Min Act: -0.1700
Data Index: 2957692 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6286. Min Act: -0.1698
Data Index: 3756868 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6025. Min Act: -0.1700
Data Index: 7261501 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.6112. Min Act: -0.1700
Data Index: 375243 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5937. Min Act: -0.1700
Data Index: 842817 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5850. Min Act: -0.1700
Data Index: 5236429 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5762. Min Act: -0.1700
Data Index: 6161427 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5762. Min Act: -0.1700
Data Index: 7035934 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5675. Min Act: -0.1693
Data Index: 5307843 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5587. Min Act: -0.1663
Data Index: 4245812 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5675. Min Act: -0.1698
Data Index: 8704935 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5762. Min Act: -0.1700
Data Index: 3430290 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5675. Min Act: -0.1700
Data Index: 7490397 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5587. Min Act: -0.1692
Data Index: 8118216 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5587. Min Act: -0.1700
Data Index: 8361606 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7242. Min Range: -1.7242
Max Act: 1.5500. Min Act: -0.1700
Data Index: 2610447 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19