Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.4928. Min Act: -0.1700
Data Index: 5310768 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.4616. Min Act: -0.1700
Data Index: 3645442 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3991. Min Act: -0.1700
Data Index: 7384899 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3678. Min Act: -0.1700
Data Index: 77668 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3991. Min Act: -0.1700
Data Index: 12424 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3678. Min Act: -0.1700
Data Index: 4928367 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3366. Min Act: -0.1700
Data Index: 2839411 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3366. Min Act: -0.1700
Data Index: 3169113 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3053. Min Act: -0.1700
Data Index: 6087821 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3053. Min Act: -0.1700
Data Index: 1765976 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.3053. Min Act: -0.1700
Data Index: 3665875 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2741. Min Act: -0.1700
Data Index: 1936182 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2741. Min Act: -0.1700
Data Index: 2577380 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2741. Min Act: -0.1700
Data Index: 6971360 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2741. Min Act: -0.1700
Data Index: 5038436 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2428. Min Act: -0.1700
Data Index: 2170352 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2741. Min Act: -0.1700
Data Index: 6974057 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2428. Min Act: -0.1700
Data Index: 89946 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2115. Min Act: -0.1700
Data Index: 6276577 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4928. Min Range: -4.4928
Max Act: 4.2115. Min Act: -0.1700
Data Index: 2533225 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19