Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.9969. Min Act: -0.1700
Data Index: 8535108 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.8719. Min Act: -0.1700
Data Index: 1780616 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.7782. Min Act: -0.1700
Data Index: 6479126 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6844. Min Act: -0.1700
Data Index: 7076046 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6844. Min Act: -0.1700
Data Index: 7023672 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6532. Min Act: -0.1700
Data Index: 8712155 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6844. Min Act: -0.1700
Data Index: 5180152 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.5907. Min Act: -0.1700
Data Index: 5990437 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6219. Min Act: -0.1700
Data Index: 5291689 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.6219. Min Act: -0.1700
Data Index: 2029519 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.5594. Min Act: -0.1700
Data Index: 3084229 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.5907. Min Act: -0.1700
Data Index: 2521101 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4969. Min Act: -0.1700
Data Index: 7617053 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.5282. Min Act: -0.1700
Data Index: 7527941 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.5282. Min Act: -0.1700
Data Index: 12698 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4969. Min Act: -0.1700
Data Index: 5175170 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4969. Min Act: -0.1700
Data Index: 6050174 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4344. Min Act: -0.1700
Data Index: 6809609 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4657. Min Act: -0.1700
Data Index: 4779692 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9969. Min Range: -6.9969
Max Act: 6.4657. Min Act: -0.1700
Data Index: 366419 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19