Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0319. Min Range: -7.0319
Max Act: 7.0319. Min Act: -0.1700
Data Index: 8535216 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.9381. Min Act: -0.1700
Data Index: 912449 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.8131. Min Act: -0.1700
Data Index: 1663149 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.8131. Min Act: -0.1700
Data Index: 6819162 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.8131. Min Act: -0.1700
Data Index: 5169456 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.8131. Min Act: -0.1700
Data Index: 7092337 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7819. Min Act: -0.1700
Data Index: 504541 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7819. Min Act: -0.1700
Data Index: 3105767 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7506. Min Act: -0.1700
Data Index: 4807736 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7506. Min Act: -0.1700
Data Index: 6943105 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3100636 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3098586 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6881. Min Act: -0.1700
Data Index: 1893405 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6881. Min Act: -0.1700
Data Index: 1369977 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 34908 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 7092338 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 4207282 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 1857885 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 328216 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0319. Min Range: -7.0319
Max Act: 6.6569. Min Act: -0.1700
Data Index: 2829611 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19