Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.6200. Min Act: -0.1700
Data Index: 7734583 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5887. Min Act: -0.1700
Data Index: 5186665 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 6733005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5575. Min Act: -0.1700
Data Index: 4857990 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 8064466 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 1786245 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 6063144 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 6301129 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.5262. Min Act: -0.1700
Data Index: 406536 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4950. Min Act: -0.1700
Data Index: 1879782 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4637. Min Act: -0.1700
Data Index: 806507 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4950. Min Act: -0.1700
Data Index: 2012034 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4637. Min Act: -0.1700
Data Index: 1358223 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4637. Min Act: -0.1700
Data Index: 3176273 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4325. Min Act: -0.1700
Data Index: 3613783 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4637. Min Act: -0.1700
Data Index: 7971789 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4637. Min Act: -0.1700
Data Index: 1866106 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4950. Min Act: -0.1700
Data Index: 5378565 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4012. Min Act: -0.1700
Data Index: 1328314 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4325. Min Act: -0.1700
Data Index: 3234656 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19