Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.2225. Min Act: -0.1700
Data Index: 5651258 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1911. Min Act: -0.1700
Data Index: 8120752 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1753. Min Act: -0.1700
Data Index: 3063000 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1596. Min Act: -0.1700
Data Index: 1752912 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1439. Min Act: -0.1700
Data Index: 1694465 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1281. Min Act: -0.1700
Data Index: 8700873 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.1124. Min Act: -0.1700
Data Index: 460641 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0966. Min Act: -0.1700
Data Index: 97037 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0966. Min Act: -0.1700
Data Index: 7472282 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0808. Min Act: -0.1700
Data Index: 4638256 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0493. Min Act: -0.1700
Data Index: 7026635 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 1694468 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 5589845 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 4845912 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 5099552 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 6566011 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 1746562 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0335. Min Act: -0.1700
Data Index: 8501405 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0019. Min Act: -0.1700
Data Index: 1716775 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2225. Min Range: -3.2225
Max Act: 3.0177. Min Act: -0.1700
Data Index: 735340 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19