Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.3135. Min Act: -0.1700
Data Index: 5423750 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.1260. Min Act: -0.1700
Data Index: 4884215 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 648018 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 7515342 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 7643399 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0635. Min Act: -0.1700
Data Index: 2129305 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3135. Min Range: -8.3135
Max Act: 8.0010. Min Act: -0.1700
Data Index: 7971290 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.9385. Min Act: -0.1700
Data Index: 5326984 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 3469258 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 7881799 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 7620256 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8760. Min Act: -0.1700
Data Index: 3900161 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8135. Min Act: -0.1700
Data Index: 1116382 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.8135. Min Act: -0.1700
Data Index: 2750463 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.7510. Min Act: -0.1700
Data Index: 8600347 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.6885. Min Act: -0.1700
Data Index: 8385283 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.6885. Min Act: -0.1700
Data Index: 5267595 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.6885. Min Act: -0.1700
Data Index: 6881532 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.6260. Min Act: -0.1700
Data Index: 6290983 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3135. Min Range: -8.3135
Max Act: 7.6573. Min Act: -0.1700
Data Index: 6571536 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19