Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5459 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.8135. Min Act: -0.1700
Data Index: 6463540 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.4385. Min Act: -0.1700
Data Index: 5393493 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.3135. Min Act: -0.1700
Data Index: 7434142 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.3135. Min Act: -0.1700
Data Index: 5363206 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.3135. Min Act: -0.1700
Data Index: 2264159 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.1260. Min Act: -0.1700
Data Index: 7058228 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 5608479 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 627395 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 4170433 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 8750170 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 817002 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 3046707 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 1245476 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 8034407 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8135. Min Range: -8.8135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 765032 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8135. Min Range: -8.8135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 168807 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8135. Min Range: -8.8135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 8312449 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8135. Min Range: -8.8135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 859097 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8135. Min Range: -8.8135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 204965 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8135. Min Range: -8.8135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 7596925 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19