Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 837 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2770. Min Act: -0.1700
Data Index: 7849497 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2770. Min Range: -7.2770
Max Act: 7.2770. Min Act: -0.1700
Data Index: 1015561 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9645. Min Act: -0.1700
Data Index: 3505047 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.9332. Min Act: -0.1700
Data Index: 1222354 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.8395. Min Act: -0.1700
Data Index: 6205637 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7770. Min Act: -0.1700
Data Index: 1925781 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8512420 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7145. Min Act: -0.1700
Data Index: 570931 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.7145. Min Act: -0.1700
Data Index: 2197037 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6520. Min Act: -0.1700
Data Index: 3412460 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 5874778 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 5798433 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1174360 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6520. Min Act: -0.1700
Data Index: 2769547 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.6207. Min Act: -0.1700
Data Index: 5003693 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5538193 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5582. Min Act: -0.1700
Data Index: 3304880 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5582. Min Act: -0.1700
Data Index: 4430293 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5270. Min Act: -0.1700
Data Index: 3540560 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2770. Min Range: -7.2770
Max Act: 6.5270. Min Act: -0.1700
Data Index: 3994122 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19