Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.7429. Min Act: -0.1700
Data Index: 2279027 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.7429. Min Act: -0.1700
Data Index: 4719494 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6803. Min Act: -0.1700
Data Index: 1379413 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6803. Min Act: -0.1700
Data Index: 5077187 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6803. Min Act: -0.1700
Data Index: 6273118 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 4278301 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 1336747 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 3164049 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 3030045 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 2945635 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 872141 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 6082113 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 5092095 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6490. Min Act: -0.1700
Data Index: 4109444 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 2881371 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 1162047 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 329864 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 1411698 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 1494009 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6178. Min Act: -0.1700
Data Index: 3341791 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19