Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0747. Min Range: -8.0747
Max Act: 8.0747. Min Act: -0.1700
Data Index: 8353085 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0747. Min Range: -8.0747
Max Act: 8.0122. Min Act: -0.1700
Data Index: 1815679 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.8247. Min Act: -0.1700
Data Index: 2174137 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.8247. Min Act: -0.1700
Data Index: 7340888 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.8872. Min Act: -0.1700
Data Index: 1575686 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.8247. Min Act: -0.1700
Data Index: 3658747 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.8247. Min Act: -0.1700
Data Index: 6175124 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.6997. Min Act: -0.1700
Data Index: 8433078 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.6997. Min Act: -0.1700
Data Index: 7244668 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5747. Min Act: -0.1700
Data Index: 5813519 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5747. Min Act: -0.1700
Data Index: 5295774 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5122. Min Act: -0.1700
Data Index: 153086 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.4497. Min Act: -0.1700
Data Index: 1234794 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5122. Min Act: -0.1700
Data Index: 7606115 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.4497. Min Act: -0.1700
Data Index: 534713 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5122. Min Act: -0.1700
Data Index: 1119228 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.3872. Min Act: -0.1700
Data Index: 502296 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5122. Min Act: -0.1700
Data Index: 7364955 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.5747. Min Act: -0.1700
Data Index: 2522542 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0747. Min Range: -8.0747
Max Act: 7.4497. Min Act: -0.1700
Data Index: 5674797 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19