Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3386. Min Range: -7.3386
Max Act: 7.3386. Min Act: -0.1700
Data Index: 1990931 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.7761. Min Act: -0.1700
Data Index: 8198065 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.6824. Min Act: -0.1700
Data Index: 7543333 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.5886. Min Act: -0.1700
Data Index: 4188686 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.5886. Min Act: -0.1700
Data Index: 304102 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.5574. Min Act: -0.1700
Data Index: 6453354 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.5574. Min Act: -0.1700
Data Index: 5793170 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4949. Min Act: -0.1700
Data Index: 5518418 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4949. Min Act: -0.1700
Data Index: 3571977 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4636. Min Act: -0.1700
Data Index: 812914 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4324. Min Act: -0.1700
Data Index: 6807699 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4324. Min Act: -0.1700
Data Index: 6777168 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 8359312 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 1934831 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4900547 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 8452668 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4718597 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.4011. Min Act: -0.1700
Data Index: 5949672 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.3699. Min Act: -0.1700
Data Index: 301092 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3386. Min Range: -7.3386
Max Act: 6.3074. Min Act: -0.1700
Data Index: 3217348 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19