Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 682 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0740. Min Range: -8.0740
Max Act: 8.0740. Min Act: -0.1700
Data Index: 7222616 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.4178. Min Act: -0.1700
Data Index: 5593406 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.3240. Min Act: -0.1700
Data Index: 6943542 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.2303. Min Act: -0.1700
Data Index: 3059036 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1990. Min Act: -0.1700
Data Index: 5216556 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.2303. Min Act: -0.1700
Data Index: 5971598 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1990. Min Act: -0.1700
Data Index: 1600383 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1990. Min Act: -0.1700
Data Index: 8728738 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1678. Min Act: -0.1700
Data Index: 8244489 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1678. Min Act: -0.1700
Data Index: 7077647 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1365. Min Act: -0.1700
Data Index: 103706 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1365. Min Act: -0.1700
Data Index: 666614 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1053. Min Act: -0.1700
Data Index: 8310745 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1365. Min Act: -0.1700
Data Index: 3091621 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1365. Min Act: -0.1700
Data Index: 6953215 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1053. Min Act: -0.1700
Data Index: 1066545 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1053. Min Act: -0.1700
Data Index: 2398465 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1053. Min Act: -0.1700
Data Index: 6290067 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.1053. Min Act: -0.1700
Data Index: 5342044 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0740. Min Range: -8.0740
Max Act: 7.0740. Min Act: -0.1700
Data Index: 6058102 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19