Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4072. Min Range: -10.4072
Max Act: 10.4072. Min Act: -0.1700
Data Index: 6111659 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4072. Min Range: -10.4072
Max Act: 10.0322. Min Act: -0.1700
Data Index: 912037 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.9697. Min Act: -0.1700
Data Index: 6904577 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.9072. Min Act: -0.1700
Data Index: 6885229 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.7822. Min Act: -0.1700
Data Index: 2046328 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.7197. Min Act: -0.1700
Data Index: 7811138 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.7197. Min Act: -0.1700
Data Index: 1991373 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.7822. Min Act: -0.1700
Data Index: 5982539 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.7197. Min Act: -0.1700
Data Index: 2953398 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 5432239 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 7334264 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 2788653 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 8455269 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.6572. Min Act: -0.1700
Data Index: 5575911 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 4667788 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5947. Min Act: -0.1700
Data Index: 4460270 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5322. Min Act: -0.1700
Data Index: 5180809 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5322. Min Act: -0.1700
Data Index: 1862306 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5322. Min Act: -0.1700
Data Index: 5863342 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4072. Min Range: -10.4072
Max Act: 9.5322. Min Act: -0.1700
Data Index: 7192742 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19