Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.5900. Min Act: -0.1700
Data Index: 379709 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.4650. Min Act: -0.1700
Data Index: 6739384 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.3713. Min Act: -0.1700
Data Index: 6285593 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.3088. Min Act: -0.1700
Data Index: 3581727 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.2150. Min Act: -0.1700
Data Index: 2586477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1838. Min Act: -0.1700
Data Index: 3087435 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1838. Min Act: -0.1700
Data Index: 41303 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1838. Min Act: -0.1700
Data Index: 3502385 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1838. Min Act: -0.1700
Data Index: 4728496 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1525. Min Act: -0.1700
Data Index: 3425844 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1213. Min Act: -0.1700
Data Index: 8449722 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1213. Min Act: -0.1700
Data Index: 4509232 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1213. Min Act: -0.1700
Data Index: 8623091 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.1213. Min Act: -0.1700
Data Index: 8791791 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0900. Min Act: -0.1700
Data Index: 1039883 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0900. Min Act: -0.1700
Data Index: 7887944 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0900. Min Act: -0.1700
Data Index: 2953164 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0588. Min Act: -0.1700
Data Index: 968967 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0588. Min Act: -0.1700
Data Index: 5915510 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5900. Min Range: -6.5900
Max Act: 6.0588. Min Act: -0.1700
Data Index: 4548511 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19