Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 791 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.9441. Min Act: -0.1700
Data Index: 4045096 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.8191. Min Act: -0.1700
Data Index: 4302079 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.7878. Min Act: -0.1700
Data Index: 330362 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.7878. Min Act: -0.1700
Data Index: 8388666 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.7253. Min Act: -0.1700
Data Index: 1443544 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.7253. Min Act: -0.1700
Data Index: 4875652 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6628. Min Act: -0.1700
Data Index: 6559458 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6628. Min Act: -0.1700
Data Index: 7396233 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6316. Min Act: -0.1700
Data Index: 2665786 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6003. Min Act: -0.1700
Data Index: 2200623 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5547413 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5125974 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6003. Min Act: -0.1700
Data Index: 872422 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5691. Min Act: -0.1700
Data Index: 4545570 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5485908 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5691. Min Act: -0.1700
Data Index: 5405288 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5691. Min Act: -0.1700
Data Index: 585404 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5378. Min Act: -0.1700
Data Index: 3660519 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5066. Min Act: -0.1700
Data Index: 6289946 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9441. Min Range: -5.9441
Max Act: 5.5378. Min Act: -0.1700
Data Index: 8376999 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19