Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.9476. Min Act: -0.1700
Data Index: 872610 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.6039. Min Act: -0.1700
Data Index: 6616445 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.5101. Min Act: -0.1700
Data Index: 2000777 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5342402 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.4476. Min Act: -0.1700
Data Index: 5427289 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.4476. Min Act: -0.1700
Data Index: 1653652 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.3851. Min Act: -0.1700
Data Index: 1084760 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.3851. Min Act: -0.1700
Data Index: 6594598 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.3539. Min Act: -0.1700
Data Index: 8506387 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.3226. Min Act: -0.1700
Data Index: 5012848 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.3226. Min Act: -0.1700
Data Index: 3144050 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.2914. Min Act: -0.1700
Data Index: 5293668 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.2601. Min Act: -0.1700
Data Index: 1087607 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.2601. Min Act: -0.1700
Data Index: 6976572 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.2289. Min Act: -0.1700
Data Index: 8280209 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.2289. Min Act: -0.1700
Data Index: 524275 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.1976. Min Act: -0.1700
Data Index: 4243358 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.1976. Min Act: -0.1700
Data Index: 5027574 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.1976. Min Act: -0.1700
Data Index: 7809452 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9476. Min Range: -5.9476
Max Act: 5.1976. Min Act: -0.1700
Data Index: 609921 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19