Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.7612. Min Act: -0.1700
Data Index: 734202 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.6517. Min Act: -0.1700
Data Index: 5133289 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.6673. Min Act: -0.1700
Data Index: 5952992 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.5108. Min Act: -0.1700
Data Index: 38596 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4951. Min Act: -0.1700
Data Index: 6311234 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4795. Min Act: -0.1700
Data Index: 5182768 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4795. Min Act: -0.1700
Data Index: 3557660 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4325. Min Act: -0.1700
Data Index: 7064197 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4168. Min Act: -0.1700
Data Index: 8615851 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4011. Min Act: -0.1700
Data Index: 7971244 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.4325. Min Act: -0.1700
Data Index: 812854 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3854. Min Act: -0.1700
Data Index: 3965161 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3697. Min Act: -0.1700
Data Index: 3702425 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3541. Min Act: -0.1700
Data Index: 2618774 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3697. Min Act: -0.1700
Data Index: 5822222 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3697. Min Act: -0.1700
Data Index: 5796872 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3541. Min Act: -0.1700
Data Index: 5430456 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3541. Min Act: -0.1700
Data Index: 3939163 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3384. Min Act: -0.1700
Data Index: 3923324 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7612. Min Range: -3.7612
Max Act: 3.3070. Min Act: -0.1700
Data Index: 6123101 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19