Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8677. Min Act: -0.1700
Data Index: 2930558 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8677. Min Act: -0.1700
Data Index: 6568778 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8677. Min Act: -0.1700
Data Index: 6937298 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3019898 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8365. Min Act: -0.1700
Data Index: 2890421 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8052. Min Act: -0.1700
Data Index: 5030612 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3155836 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3008106 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7740. Min Act: -0.1700
Data Index: 98894 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7740. Min Act: -0.1700
Data Index: 3772356 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7740. Min Act: -0.1700
Data Index: 28308 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4422651 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 2618889 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 3386804 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7740. Min Act: -0.1700
Data Index: 2562884 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 1852931 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 3984113 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 4597330 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7115. Min Act: -0.1700
Data Index: 2904589 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8677. Min Range: -4.8677
Max Act: 4.7115. Min Act: -0.1700
Data Index: 3515647 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19