Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 979552 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8248. Min Act: -0.1700
Data Index: 4444389 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6373. Min Act: -0.1700
Data Index: 6798255 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.5123. Min Act: -0.1700
Data Index: 4545104 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.4810. Min Act: -0.1700
Data Index: 8044028 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3873. Min Act: -0.1700
Data Index: 6669145 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.4498. Min Act: -0.1700
Data Index: 8702364 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.4185. Min Act: -0.1700
Data Index: 4260402 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3873. Min Act: -0.1700
Data Index: 4737393 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3873. Min Act: -0.1700
Data Index: 8068413 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3248. Min Act: -0.1700
Data Index: 3151597 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.4185. Min Act: -0.1700
Data Index: 7126830 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3560. Min Act: -0.1700
Data Index: 2384554 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.2935. Min Act: -0.1700
Data Index: 4908659 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3560. Min Act: -0.1700
Data Index: 4666835 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3248. Min Act: -0.1700
Data Index: 6839172 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4291901 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3248. Min Act: -0.1700
Data Index: 1412040 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.3873. Min Act: -0.1700
Data Index: 6356574 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.2935. Min Act: -0.1700
Data Index: 6440458 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19