Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.8895. Min Act: -0.1700
Data Index: 8070491 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.7332. Min Act: -0.1700
Data Index: 6862308 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.6395. Min Act: -0.1700
Data Index: 6417779 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.5457. Min Act: -0.1700
Data Index: 528154 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.5145. Min Act: -0.1700
Data Index: 251192 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.5145. Min Act: -0.1700
Data Index: 5225152 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.5145. Min Act: -0.1700
Data Index: 7664202 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.5145. Min Act: -0.1700
Data Index: 4614963 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4832. Min Act: -0.1700
Data Index: 1392456 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4832. Min Act: -0.1700
Data Index: 7658469 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4520. Min Act: -0.1700
Data Index: 5270782 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4520. Min Act: -0.1700
Data Index: 3371961 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4832. Min Act: -0.1700
Data Index: 5001245 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4520. Min Act: -0.1700
Data Index: 4559549 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6855519 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.3895. Min Act: -0.1700
Data Index: 3518692 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.3895. Min Act: -0.1700
Data Index: 697755 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.3582. Min Act: -0.1700
Data Index: 6737163 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.3582. Min Act: -0.1700
Data Index: 2117803 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8895. Min Range: -5.8895
Max Act: 5.3582. Min Act: -0.1700
Data Index: 8536472 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19