Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.3579. Min Act: -0.1700
Data Index: 8120057 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.3579. Min Act: -0.1700
Data Index: 4945034 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.3267. Min Act: -0.1700
Data Index: 4991830 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.3267. Min Act: -0.1700
Data Index: 8701888 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2642. Min Act: -0.1700
Data Index: 7585262 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.3267. Min Act: -0.1700
Data Index: 7185153 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2642. Min Act: -0.1698
Data Index: 148071 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2954. Min Act: -0.1694
Data Index: 7595457 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2642. Min Act: -0.1700
Data Index: 8768534 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2954. Min Act: -0.1700
Data Index: 226088 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2329. Min Act: -0.1699
Data Index: 4614158 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2329. Min Act: -0.1700
Data Index: 7106796 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2642. Min Act: -0.1700
Data Index: 5722228 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2016. Min Act: -0.1700
Data Index: 4914696 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2329. Min Act: -0.1700
Data Index: 512561 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2954. Min Act: -0.1699
Data Index: 2327620 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2016. Min Act: -0.1700
Data Index: 2385778 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2329. Min Act: -0.1699
Data Index: 1565162 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.1704. Min Act: -0.1700
Data Index: 2333274 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3579. Min Range: -4.3579
Max Act: 4.2016. Min Act: -0.1700
Data Index: 964094 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19