Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2793. Min Act: -0.1700
Data Index: 6134918 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2705. Min Act: -0.1668
Data Index: 6427449 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2617. Min Act: -0.1700
Data Index: 3499547 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2617. Min Act: -0.1688
Data Index: 4187207 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2529. Min Act: -0.1700
Data Index: 5744500 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2617. Min Act: -0.1693
Data Index: 2148021 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2441. Min Act: -0.1670
Data Index: 6427452 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2441. Min Act: -0.1536
Data Index: 2148020 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2264. Min Act: -0.1544
Data Index: 2148019 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2264. Min Act: -0.1686
Data Index: 3141026 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2176. Min Act: -0.1697
Data Index: 4266882 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2176. Min Act: -0.1700
Data Index: 7182555 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2088. Min Act: -0.1700
Data Index: 7803413 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2088. Min Act: -0.1699
Data Index: 7893419 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2000. Min Act: -0.1700
Data Index: 6853694 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.1824. Min Act: -0.1696
Data Index: 1332583 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.2000. Min Act: -0.1700
Data Index: 1231124 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.1912. Min Act: -0.1690
Data Index: 3930111 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.1824. Min Act: -0.1688
Data Index: 1005026 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2793. Min Range: -1.2793
Max Act: 1.1824. Min Act: -0.1611
Data Index: 3517182 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19