Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.8810. Min Act: -0.1700
Data Index: 8384084 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.8497. Min Act: -0.1700
Data Index: 5937098 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4929615 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7872. Min Act: -0.1700
Data Index: 5937100 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7872. Min Act: -0.1700
Data Index: 5937099 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7560. Min Act: -0.1700
Data Index: 7939024 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7560. Min Act: -0.1700
Data Index: 269965 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3000169 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.6935. Min Act: -0.1700
Data Index: 6685501 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5685. Min Act: -0.1700
Data Index: 442397 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5997. Min Act: -0.1700
Data Index: 1226858 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5997. Min Act: -0.1700
Data Index: 7196814 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5997. Min Act: -0.1700
Data Index: 5085590 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5997. Min Act: -0.1700
Data Index: 4475464 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5685. Min Act: -0.1700
Data Index: 6787983 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5372. Min Act: -0.1700
Data Index: 4929616 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5372. Min Act: -0.1700
Data Index: 2256735 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5372. Min Act: -0.1700
Data Index: 8441162 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5372. Min Act: -0.1700
Data Index: 1761617 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8810. Min Range: -4.8810
Max Act: 4.5060. Min Act: -0.1700
Data Index: 6075834 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19