Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5408 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.2838. Min Act: -0.1700
Data Index: 8074516 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 8613875 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.9088. Min Act: -0.1700
Data Index: 7054609 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.8150. Min Act: -0.1700
Data Index: 1622579 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7838. Min Act: -0.1700
Data Index: 5402761 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 2228946 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 5043407 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 8388843 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 4360653 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 2479616 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 870709 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 1479030 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7213. Min Act: -0.1700
Data Index: 369233 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.7525. Min Act: -0.1700
Data Index: 5457042 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6588. Min Act: -0.1700
Data Index: 2466148 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6900. Min Act: -0.1700
Data Index: 5993274 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6900. Min Act: -0.1700
Data Index: 2709329 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6588. Min Act: -0.1700
Data Index: 4214218 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6900. Min Act: -0.1700
Data Index: 1504685 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.6900. Min Act: -0.1700
Data Index: 588220 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19