Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1363. Min Range: -4.1363
Max Act: 4.1363. Min Act: -0.1700
Data Index: 2991263 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.9175. Min Act: -0.1700
Data Index: 8346951 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.9488. Min Act: -0.1700
Data Index: 5328199 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3275660 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.9175. Min Act: -0.1700
Data Index: 4198356 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3272674 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8863. Min Act: -0.1700
Data Index: 5108804 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8550. Min Act: -0.1700
Data Index: 7663975 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8550. Min Act: -0.1700
Data Index: 3064922 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8550. Min Act: -0.1700
Data Index: 5150755 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8237. Min Act: -0.1700
Data Index: 6026368 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8237. Min Act: -0.1700
Data Index: 2499660 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8237. Min Act: -0.1700
Data Index: 4893136 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8237. Min Act: -0.1700
Data Index: 8405000 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.8237. Min Act: -0.1700
Data Index: 4665995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.7924. Min Act: -0.1700
Data Index: 2214450 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.7924. Min Act: -0.1700
Data Index: 6538236 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.7924. Min Act: -0.1700
Data Index: 7615248 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.7924. Min Act: -0.1700
Data Index: 6534911 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1363. Min Range: -4.1363
Max Act: 3.7924. Min Act: -0.1700
Data Index: 7771953 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19