Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.5582. Min Act: -0.1700
Data Index: 7292937 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.4020. Min Act: -0.1700
Data Index: 6115667 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.3082. Min Act: -0.1700
Data Index: 4208475 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.3082. Min Act: -0.1700
Data Index: 4139140 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.2770. Min Act: -0.1700
Data Index: 7945056 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.2770. Min Act: -0.1700
Data Index: 8281730 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.2145. Min Act: -0.1700
Data Index: 5577838 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.2457. Min Act: -0.1700
Data Index: 6576218 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1520. Min Act: -0.1700
Data Index: 2591141 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1832. Min Act: -0.1700
Data Index: 5584122 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1207. Min Act: -0.1700
Data Index: 117993 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1520. Min Act: -0.1700
Data Index: 2080145 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1520. Min Act: -0.1700
Data Index: 5609044 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1520. Min Act: -0.1700
Data Index: 7415720 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1207. Min Act: -0.1700
Data Index: 1601087 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1207. Min Act: -0.1700
Data Index: 8763511 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1207. Min Act: -0.1700
Data Index: 6362391 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.1207. Min Act: -0.1700
Data Index: 7173509 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.0895. Min Act: -0.1700
Data Index: 8585133 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5582. Min Range: -7.5582
Max Act: 7.0582. Min Act: -0.1700
Data Index: 8397740 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19