Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 198 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.9938. Min Act: -0.1700
Data Index: 872525 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.9147. Min Act: -0.1700
Data Index: 1145934 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8671. Min Act: -0.1700
Data Index: 533228 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8512. Min Act: -0.1700
Data Index: 15834 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8194. Min Act: -0.1700
Data Index: 1358863 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8035. Min Act: -0.1700
Data Index: 983965 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8035. Min Act: -0.1700
Data Index: 1196813 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.8035. Min Act: -0.1700
Data Index: 179110 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7875. Min Act: -0.1700
Data Index: 738635 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7875. Min Act: -0.1700
Data Index: 915662 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1587500 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7716. Min Act: -0.1700
Data Index: 1145526 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 615302 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 195844 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7716. Min Act: -0.1700
Data Index: 759115 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 38501 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 976990 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 42487 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 146187 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9938. Min Range: -2.9938
Max Act: 2.7556. Min Act: -0.1700
Data Index: 205758 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19