Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.2156. Min Act: -0.1700
Data Index: 5503273 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1824. Min Act: -0.1700
Data Index: 2197328 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1990. Min Act: -0.1700
Data Index: 8421459 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1824. Min Act: -0.1700
Data Index: 3572761 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1491. Min Act: -0.1700
Data Index: 2327480 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1658. Min Act: -0.1700
Data Index: 7403202 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1658. Min Act: -0.1700
Data Index: 4107017 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1491. Min Act: -0.1700
Data Index: 2596112 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1157. Min Act: -0.1700
Data Index: 6918328 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 201845 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 7627696 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 8350233 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 725645 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.0990. Min Act: -0.1700
Data Index: 8336802 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 8622820 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.0990. Min Act: -0.1700
Data Index: 3269733 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1157. Min Act: -0.1700
Data Index: 3249945 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1157. Min Act: -0.1700
Data Index: 3142933 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1157. Min Act: -0.1700
Data Index: 1418681 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2156. Min Range: -2.2156
Max Act: 2.1324. Min Act: -0.1700
Data Index: 2198216 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19