Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.5865. Min Act: -0.1700
Data Index: 4626903 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.3990. Min Act: -0.1700
Data Index: 2025691 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.3365. Min Act: -0.1700
Data Index: 399517 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.3365. Min Act: -0.1700
Data Index: 5250187 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.3365. Min Act: -0.1700
Data Index: 1348037 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.3365. Min Act: -0.1700
Data Index: 3378896 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2740. Min Act: -0.1700
Data Index: 7404633 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2740. Min Act: -0.1700
Data Index: 8411856 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2740. Min Act: -0.1700
Data Index: 6078667 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2740. Min Act: -0.1700
Data Index: 4448498 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1700
Data Index: 2493039 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1700
Data Index: 844609 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1700
Data Index: 389206 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1699
Data Index: 4247489 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1700
Data Index: 5751190 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.1490. Min Act: -0.1700
Data Index: 6095976 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.1490. Min Act: -0.1700
Data Index: 6175609 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.1490. Min Act: -0.1700
Data Index: 804773 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.2115. Min Act: -0.1700
Data Index: 3568558 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5865. Min Range: -8.5865
Max Act: 8.1490. Min Act: -0.1700
Data Index: 5541197 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19