Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.1674. Min Act: -0.1700
Data Index: 1028849 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1664784 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1028848 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.0111. Min Act: -0.1699
Data Index: 7871264 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1028845 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1674. Min Range: -5.1674
Max Act: 5.0111. Min Act: -0.1700
Data Index: 1028832 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.9174. Min Act: -0.1700
Data Index: 7871278 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1519950 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8549. Min Act: -0.1696
Data Index: 7871241 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8549. Min Act: -0.1700
Data Index: 7871274 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 4811830 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8549. Min Act: -0.1700
Data Index: 7871272 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 442132 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7924. Min Act: -0.1700
Data Index: 4853717 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1674
Data Index: 1247699 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1028857 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1697
Data Index: 7871261 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1607511 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.7611. Min Act: -0.1700
Data Index: 1028834 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1674. Min Range: -5.1674
Max Act: 4.8236. Min Act: -0.1687
Data Index: 7871263 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19