Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4279 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.7601. Min Act: -0.1700
Data Index: 6715026 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.2289. Min Act: -0.1700
Data Index: 1410502 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.1039. Min Act: -0.1700
Data Index: 4225015 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.0726. Min Act: -0.1700
Data Index: 7805359 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8121395 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7601. Min Range: -6.7601
Max Act: 6.0101. Min Act: -0.1700
Data Index: 1905661 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.8851. Min Act: -0.1700
Data Index: 2734390 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.8539. Min Act: -0.1700
Data Index: 6555474 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.8226. Min Act: -0.1700
Data Index: 6381898 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.8226. Min Act: -0.1700
Data Index: 7773079 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7601. Min Act: -0.1700
Data Index: 4064049 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4513087 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2000628 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7914. Min Act: -0.1700
Data Index: 3400911 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7601. Min Act: -0.1700
Data Index: 7727425 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6552380 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.7289. Min Act: -0.1700
Data Index: 7824369 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.6976. Min Act: -0.1700
Data Index: 6395937 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.6664. Min Act: -0.1700
Data Index: 2596894 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7601. Min Range: -6.7601
Max Act: 5.6351. Min Act: -0.1700
Data Index: 988102 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19