Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.6873. Min Act: -0.1700
Data Index: 140228 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.6248. Min Act: -0.1700
Data Index: 8633646 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.5935. Min Act: -0.1700
Data Index: 6833621 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.5310. Min Act: -0.1700
Data Index: 77579 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.5310. Min Act: -0.1700
Data Index: 7355335 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4998. Min Act: -0.1700
Data Index: 5977262 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4998. Min Act: -0.1700
Data Index: 4158575 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4685. Min Act: -0.1700
Data Index: 8184896 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4685. Min Act: -0.1700
Data Index: 4263096 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4685. Min Act: -0.1700
Data Index: 8171730 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4373. Min Act: -0.1700
Data Index: 4412903 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4373. Min Act: -0.1700
Data Index: 645847 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4373. Min Act: -0.1700
Data Index: 8680879 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4373. Min Act: -0.1700
Data Index: 6136935 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4373. Min Act: -0.1700
Data Index: 8623824 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.4060. Min Act: -0.1700
Data Index: 5458450 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.3748. Min Act: -0.1700
Data Index: 4234101 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.3748. Min Act: -0.1700
Data Index: 1145884 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.3748. Min Act: -0.1700
Data Index: 4042598 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6873. Min Range: -5.6873
Max Act: 5.3748. Min Act: -0.1700
Data Index: 1150300 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19