Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.4280. Min Act: -0.1700
Data Index: 3282459 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2868. Min Act: -0.1700
Data Index: 7682166 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2868. Min Act: -0.1700
Data Index: 3277023 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2868. Min Act: -0.1700
Data Index: 3282460 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2554. Min Act: -0.1700
Data Index: 6643477 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2397. Min Act: -0.1700
Data Index: 2168458 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2397. Min Act: -0.1700
Data Index: 7583143 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2554. Min Act: -0.1700
Data Index: 7303954 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2397. Min Act: -0.1700
Data Index: 2122782 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2397. Min Act: -0.1700
Data Index: 6328423 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2397. Min Act: -0.1700
Data Index: 2614602 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2240. Min Act: -0.1700
Data Index: 5422826 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2083. Min Act: -0.1700
Data Index: 1439444 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2083. Min Act: -0.1700
Data Index: 3463593 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.1925. Min Act: -0.1700
Data Index: 4570578 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2083. Min Act: -0.1700
Data Index: 5256469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.1768. Min Act: -0.1700
Data Index: 2090487 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.1768. Min Act: -0.1700
Data Index: 6865154 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.1925. Min Act: -0.1700
Data Index: 2219469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4280. Min Range: -3.4280
Max Act: 3.2083. Min Act: -0.1700
Data Index: 5156472 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19