Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3824. Min Range: -4.3824
Max Act: 4.3824. Min Act: -0.1700
Data Index: 2463810 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3824. Min Range: -4.3824
Max Act: 4.1636. Min Act: -0.1700
Data Index: 461415 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3824. Min Range: -4.3824
Max Act: 4.1323. Min Act: -0.1700
Data Index: 1164717 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3824. Min Range: -4.3824
Max Act: 4.1011. Min Act: -0.1700
Data Index: 4289939 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3824. Min Range: -4.3824
Max Act: 4.1011. Min Act: -0.1700
Data Index: 3271 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9760. Min Act: -0.1700
Data Index: 5381569 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9760. Min Act: -0.1700
Data Index: 2173372 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9448. Min Act: -0.1700
Data Index: 5358629 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9448. Min Act: -0.1700
Data Index: 3359652 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9448. Min Act: -0.1700
Data Index: 3903766 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4126377 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8822. Min Act: -0.1700
Data Index: 3495521 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9448. Min Act: -0.1700
Data Index: 1373510 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.9135. Min Act: -0.1700
Data Index: 183707 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8822. Min Act: -0.1700
Data Index: 5263690 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4786562 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8822. Min Act: -0.1700
Data Index: 2745074 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8510. Min Act: -0.1700
Data Index: 6114717 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8197. Min Act: -0.1700
Data Index: 6534906 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3824. Min Range: -4.3824
Max Act: 3.8197. Min Act: -0.1700
Data Index: 6000747 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19