Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.4431. Min Act: -0.1700
Data Index: 901475 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.3647. Min Act: -0.1700
Data Index: 7727646 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.3333. Min Act: -0.1700
Data Index: 8548910 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.3019. Min Act: -0.1700
Data Index: 4492400 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2705. Min Act: -0.1700
Data Index: 2473618 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2548. Min Act: -0.1700
Data Index: 5406910 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2391. Min Act: -0.1700
Data Index: 7016700 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2548. Min Act: -0.1700
Data Index: 2427124 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2077. Min Act: -0.1700
Data Index: 3983864 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.2077. Min Act: -0.1700
Data Index: 4834025 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1920. Min Act: -0.1700
Data Index: 3349996 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1762. Min Act: -0.1700
Data Index: 6095693 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1605. Min Act: -0.1700
Data Index: 1966090 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1605. Min Act: -0.1700
Data Index: 2972620 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1605. Min Act: -0.1700
Data Index: 8344272 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1605. Min Act: -0.1700
Data Index: 6831116 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1605. Min Act: -0.1700
Data Index: 7903106 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1290. Min Act: -0.1700
Data Index: 4957063 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1447. Min Act: -0.1700
Data Index: 7656133 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4431. Min Range: -3.4431
Max Act: 3.1447. Min Act: -0.1700
Data Index: 865373 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19