Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.8235. Min Act: -0.1700
Data Index: 7141924 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.8063. Min Act: -0.1700
Data Index: 6258671 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7891. Min Act: -0.1697
Data Index: 2197554 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7977. Min Act: -0.1700
Data Index: 8060425 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7805. Min Act: -0.1700
Data Index: 5269792 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7719. Min Act: -0.1700
Data Index: 1804441 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7805. Min Act: -0.1700
Data Index: 5300543 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7460. Min Act: -0.1700
Data Index: 1804440 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7546. Min Act: -0.1699
Data Index: 702103 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7546. Min Act: -0.1699
Data Index: 7141935 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7460. Min Act: -0.1700
Data Index: 7308689 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7460. Min Act: -0.1699
Data Index: 2577443 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7546. Min Act: -0.1700
Data Index: 4544323 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7546. Min Act: -0.1700
Data Index: 4020049 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 7330086 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 1862147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 4544325 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 2197555 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 1327526 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8235. Min Range: -1.8235
Max Act: 1.7374. Min Act: -0.1700
Data Index: 3442888 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19