Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0207. Min Range: -5.0207
Max Act: 5.0207. Min Act: -0.1700
Data Index: 7184565 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.9582. Min Act: -0.1700
Data Index: 505456 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.9582. Min Act: -0.1700
Data Index: 1269007 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.7082. Min Act: -0.1700
Data Index: 5978883 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.7082. Min Act: -0.1700
Data Index: 5777111 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.7707. Min Act: -0.1700
Data Index: 8151255 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.7082. Min Act: -0.1700
Data Index: 6610224 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.6769. Min Act: -0.1700
Data Index: 5911598 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.6769. Min Act: -0.1700
Data Index: 2099285 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.6144. Min Act: -0.1700
Data Index: 547889 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.6144. Min Act: -0.1700
Data Index: 455645 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5832. Min Act: -0.1700
Data Index: 8040182 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.6144. Min Act: -0.1700
Data Index: 7052676 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5519. Min Act: -0.1700
Data Index: 5801979 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5832. Min Act: -0.1700
Data Index: 6902976 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5832. Min Act: -0.1700
Data Index: 2385873 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5519. Min Act: -0.1700
Data Index: 7754544 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5207. Min Act: -0.1700
Data Index: 2755691 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5519. Min Act: -0.1700
Data Index: 3022616 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0207. Min Range: -5.0207
Max Act: 4.5519. Min Act: -0.1700
Data Index: 4512236 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19