Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.9595. Min Act: -0.1700
Data Index: 8292064 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.9282. Min Act: -0.1700
Data Index: 3363696 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.8345. Min Act: -0.1700
Data Index: 3805272 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.7407. Min Act: -0.1700
Data Index: 8064151 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.5845. Min Act: -0.1700
Data Index: 5672154 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.5532. Min Act: -0.1700
Data Index: 3296453 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.5220. Min Act: -0.1700
Data Index: 5323399 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3657. Min Act: -0.1700
Data Index: 3645552 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3657. Min Act: -0.1700
Data Index: 4078045 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3345. Min Act: -0.1700
Data Index: 2083110 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3345. Min Act: -0.1700
Data Index: 3043415 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2720. Min Act: -0.1700
Data Index: 4954922 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3032. Min Act: -0.1700
Data Index: 6418092 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.3032. Min Act: -0.1700
Data Index: 122707 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2720. Min Act: -0.1700
Data Index: 6497876 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2095. Min Act: -0.1700
Data Index: 3126271 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2095. Min Act: -0.1700
Data Index: 7169454 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2095. Min Act: -0.1700
Data Index: 4081179 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.2095. Min Act: -0.1700
Data Index: 2831221 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9595. Min Range: -6.9595
Max Act: 6.1782. Min Act: -0.1700
Data Index: 234198 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19