Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.8853. Min Act: -0.1700
Data Index: 8748042 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.8853. Min Act: -0.1700
Data Index: 3723847 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.8228. Min Act: -0.1700
Data Index: 1673114 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.7916. Min Act: -0.1700
Data Index: 7131525 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.7916. Min Act: -0.1700
Data Index: 8695851 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.7291. Min Act: -0.1700
Data Index: 2355109 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6978. Min Act: -0.1700
Data Index: 846061 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6978. Min Act: -0.1700
Data Index: 7018621 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6978. Min Act: -0.1700
Data Index: 8452890 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6666. Min Act: -0.1700
Data Index: 5143552 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6666. Min Act: -0.1700
Data Index: 3200591 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6339222 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6242832 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6353. Min Act: -0.1700
Data Index: 1795853 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6041. Min Act: -0.1700
Data Index: 4475182 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6041. Min Act: -0.1700
Data Index: 2331381 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6041. Min Act: -0.1700
Data Index: 3012749 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.6041. Min Act: -0.1700
Data Index: 3862930 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.5728. Min Act: -0.1700
Data Index: 3118591 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8853. Min Range: -5.8853
Max Act: 5.5103. Min Act: -0.1700
Data Index: 5495691 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19