Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1778. Min Range: -6.1778
Max Act: 6.1778. Min Act: -0.1700
Data Index: 4010729 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1778. Min Range: -6.1778
Max Act: 6.0841. Min Act: -0.1700
Data Index: 6616139 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.6466. Min Act: -0.1700
Data Index: 8803754 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.6466. Min Act: -0.1700
Data Index: 5777721 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.6778. Min Act: -0.1700
Data Index: 4461471 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.6466. Min Act: -0.1700
Data Index: 5693720 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.6466. Min Act: -0.1700
Data Index: 456631 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5841. Min Act: -0.1700
Data Index: 3807017 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 7445605 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5296032 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 1965469 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 8645564 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5216. Min Act: -0.1700
Data Index: 5715134 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5216. Min Act: -0.1700
Data Index: 2718407 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 8485819 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.5216. Min Act: -0.1700
Data Index: 367862 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2312550 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.4591. Min Act: -0.1700
Data Index: 8203853 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.4591. Min Act: -0.1700
Data Index: 6256871 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1778. Min Range: -6.1778
Max Act: 5.4591. Min Act: -0.1700
Data Index: 3061135 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19