Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1202482 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.5507. Min Act: -0.1700
Data Index: 4197566 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.5194. Min Act: -0.1700
Data Index: 7836110 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.4882. Min Act: -0.1700
Data Index: 1109817 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.5194. Min Act: -0.1700
Data Index: 7595892 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.4257. Min Act: -0.1700
Data Index: 6844107 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3944. Min Act: -0.1700
Data Index: 5378192 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3944. Min Act: -0.1700
Data Index: 3559920 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3632. Min Act: -0.1700
Data Index: 8481551 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3632. Min Act: -0.1700
Data Index: 6724297 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3632. Min Act: -0.1700
Data Index: 6489075 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3632. Min Act: -0.1700
Data Index: 3966973 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3319. Min Act: -0.1700
Data Index: 7727400 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3319. Min Act: -0.1700
Data Index: 782168 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3319. Min Act: -0.1700
Data Index: 8293626 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.2694. Min Act: -0.1700
Data Index: 4484616 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3007. Min Act: -0.1700
Data Index: 3116572 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.2694. Min Act: -0.1700
Data Index: 5343104 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3007. Min Act: -0.1700
Data Index: 5783698 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6757. Min Range: -5.6757
Max Act: 5.3007. Min Act: -0.1700
Data Index: 8363150 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19