Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.9439. Min Act: -0.1700
Data Index: 4145343 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.6001. Min Act: -0.1700
Data Index: 4063496 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.5376. Min Act: -0.1700
Data Index: 7878725 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.5689. Min Act: -0.1700
Data Index: 4337016 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.5689. Min Act: -0.1700
Data Index: 2430129 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.5376. Min Act: -0.1700
Data Index: 7091150 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.5376. Min Act: -0.1700
Data Index: 7785754 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.4439. Min Act: -0.1700
Data Index: 3793294 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.4439. Min Act: -0.1700
Data Index: 3815922 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.4126. Min Act: -0.1700
Data Index: 8583872 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3814. Min Act: -0.1700
Data Index: 1489077 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.4126. Min Act: -0.1700
Data Index: 1455245 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3501. Min Act: -0.1700
Data Index: 8085253 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3501. Min Act: -0.1700
Data Index: 1650902 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3501. Min Act: -0.1700
Data Index: 7338694 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3189. Min Act: -0.1700
Data Index: 7752146 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3189. Min Act: -0.1700
Data Index: 4208293 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3501. Min Act: -0.1700
Data Index: 3892959 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3189. Min Act: -0.1700
Data Index: 2231303 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9439. Min Range: -5.9439
Max Act: 5.3189. Min Act: -0.1700
Data Index: 2310577 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19