Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8218. Min Range: -6.8218
Max Act: 6.8218. Min Act: -0.1700
Data Index: 369613 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8218. Min Range: -6.8218
Max Act: 6.0406. Min Act: -0.1700
Data Index: 3810072 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8218. Min Range: -6.8218
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7347810 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.9781. Min Act: -0.1700
Data Index: 1406178 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.9468. Min Act: -0.1700
Data Index: 2704440 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.8843. Min Act: -0.1700
Data Index: 8710783 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.8531. Min Act: -0.1700
Data Index: 2211650 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.8218. Min Act: -0.1700
Data Index: 347394 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.8218. Min Act: -0.1700
Data Index: 5970928 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.7593. Min Act: -0.1700
Data Index: 6956802 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.7281. Min Act: -0.1700
Data Index: 404941 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.7593. Min Act: -0.1700
Data Index: 7665745 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.7281. Min Act: -0.1700
Data Index: 801195 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6968. Min Act: -0.1700
Data Index: 2117113 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6968. Min Act: -0.1700
Data Index: 6097928 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6968. Min Act: -0.1700
Data Index: 7341336 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6656. Min Act: -0.1700
Data Index: 7492547 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6343. Min Act: -0.1700
Data Index: 2846535 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6343. Min Act: -0.1700
Data Index: 5655006 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8218. Min Range: -6.8218
Max Act: 5.6343. Min Act: -0.1700
Data Index: 6878708 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19