Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5887. Min Act: -0.1700
Data Index: 7842381 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5887. Min Act: -0.1700
Data Index: 4148133 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5574. Min Act: -0.1700
Data Index: 2135004 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5574. Min Act: -0.1700
Data Index: 1841176 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5574. Min Act: -0.1700
Data Index: 5819059 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5262. Min Act: -0.1700
Data Index: 4682587 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4949. Min Act: -0.1700
Data Index: 22922 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4949. Min Act: -0.1700
Data Index: 2395667 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.5262. Min Act: -0.1700
Data Index: 1135904 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4949. Min Act: -0.1700
Data Index: 7840050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4949. Min Act: -0.1700
Data Index: 8020954 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4637. Min Act: -0.1700
Data Index: 8340312 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4324. Min Act: -0.1700
Data Index: 7619042 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4324. Min Act: -0.1700
Data Index: 4994263 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4324. Min Act: -0.1700
Data Index: 5888700 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7715315 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.4012. Min Act: -0.1700
Data Index: 7618119 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7297624 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.3387. Min Act: -0.1700
Data Index: 2887417 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5887. Min Range: -4.5887
Max Act: 4.3699. Min Act: -0.1700
Data Index: 42023 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19