Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 229 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5191. Min Range: -6.5191
Max Act: 6.5191. Min Act: -0.1700
Data Index: 4658653 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5191. Min Range: -6.5191
Max Act: 6.3004. Min Act: -0.1700
Data Index: 3322005 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5191. Min Range: -6.5191
Max Act: 6.0191. Min Act: -0.1700
Data Index: 5425700 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.9254. Min Act: -0.1700
Data Index: 8528383 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.8941. Min Act: -0.1700
Data Index: 6019567 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.7066. Min Act: -0.1700
Data Index: 5563503 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.7066. Min Act: -0.1700
Data Index: 8195622 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6754. Min Act: -0.1700
Data Index: 6019566 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6754. Min Act: -0.1700
Data Index: 2197776 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6754. Min Act: -0.1700
Data Index: 6396426 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6441. Min Act: -0.1700
Data Index: 579046 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6441. Min Act: -0.1700
Data Index: 8240594 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6441. Min Act: -0.1700
Data Index: 1339721 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 4304587 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3258111 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6087762 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3258113 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7687983 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7328251 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5191. Min Range: -6.5191
Max Act: 5.5816. Min Act: -0.1700
Data Index: 581455 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19