Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.6681. Min Act: -0.1700
Data Index: 8804494 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.4806. Min Act: -0.1700
Data Index: 3443598 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.3243. Min Act: -0.1700
Data Index: 6859797 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5943021 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.2306. Min Act: -0.1700
Data Index: 3443600 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.1993. Min Act: -0.1700
Data Index: 71959 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.1993. Min Act: -0.1700
Data Index: 8804495 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.1993. Min Act: -0.1700
Data Index: 854133 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6681. Min Range: -7.6681
Max Act: 7.1368. Min Act: -0.1700
Data Index: 7972618 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.9181. Min Act: -0.1700
Data Index: 5870304 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.9181. Min Act: -0.1700
Data Index: 4553722 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.7931. Min Act: -0.1700
Data Index: 5543099 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2205184 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 8172110 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.6681. Min Act: -0.1700
Data Index: 6701903 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.5743. Min Act: -0.1700
Data Index: 5833849 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.4806. Min Act: -0.1700
Data Index: 7966388 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.5118. Min Act: -0.1700
Data Index: 8651103 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.5118. Min Act: -0.1700
Data Index: 8627805 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6681. Min Range: -7.6681
Max Act: 6.4806. Min Act: -0.1700
Data Index: 767483 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19