Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5996 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1358. Min Range: -8.1358
Max Act: 8.1358. Min Act: -0.1700
Data Index: 4371106 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1358. Min Range: -8.1358
Max Act: 8.0733. Min Act: -0.1700
Data Index: 6232149 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.9483. Min Act: -0.1700
Data Index: 4060671 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.8858. Min Act: -0.1700
Data Index: 2951840 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7920. Min Act: -0.1700
Data Index: 5453852 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.8233. Min Act: -0.1700
Data Index: 6219636 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7920. Min Act: -0.1700
Data Index: 1239984 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7920. Min Act: -0.1700
Data Index: 4763926 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7920. Min Act: -0.1700
Data Index: 5039041 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7608. Min Act: -0.1700
Data Index: 6183810 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7608. Min Act: -0.1700
Data Index: 5745850 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7608. Min Act: -0.1700
Data Index: 193671 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.7295. Min Act: -0.1700
Data Index: 5946910 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6983. Min Act: -0.1700
Data Index: 4213169 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6983. Min Act: -0.1700
Data Index: 266907 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6358. Min Act: -0.1700
Data Index: 1851732 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6670. Min Act: -0.1700
Data Index: 3168536 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6358. Min Act: -0.1700
Data Index: 5777417 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6358. Min Act: -0.1700
Data Index: 562774 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1358. Min Range: -8.1358
Max Act: 7.6670. Min Act: -0.1700
Data Index: 532017 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19