Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6033 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2115. Min Range: -8.2115
Max Act: 8.2115. Min Act: -0.1700
Data Index: 1525247 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2115. Min Range: -8.2115
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4083845 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2115. Min Range: -8.2115
Max Act: 8.0240. Min Act: -0.1700
Data Index: 4189729 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2115. Min Range: -8.2115
Max Act: 8.0240. Min Act: -0.1700
Data Index: 8691810 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.9615. Min Act: -0.1700
Data Index: 8709384 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.9615. Min Act: -0.1700
Data Index: 8548014 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.8990. Min Act: -0.1700
Data Index: 3953799 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.8365. Min Act: -0.1700
Data Index: 7363813 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.8990. Min Act: -0.1700
Data Index: 1292539 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.8990. Min Act: -0.1700
Data Index: 7242677 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.8365. Min Act: -0.1700
Data Index: 1584106 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7740. Min Act: -0.1700
Data Index: 311455 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7740. Min Act: -0.1700
Data Index: 7394930 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7740. Min Act: -0.1700
Data Index: 8423103 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7740. Min Act: -0.1700
Data Index: 762208 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7740. Min Act: -0.1700
Data Index: 8625503 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 3211599 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 2311813 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 3333493 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2115. Min Range: -8.2115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 6993460 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19