Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 102 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.1006. Min Act: -0.0001
Data Index: 61050 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.1107. Min Act: -0.0001
Data Index: 1020414 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0991. Min Act: -0.0001
Data Index: 36151 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0980. Min Act: -0.0001
Data Index: 234801 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0775. Min Act: -0.0001
Data Index: 1287059 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0912. Min Act: -0.0001
Data Index: 1200595 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0907. Min Act: -0.0001
Data Index: 702084 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0918. Min Act: -0.0001
Data Index: 236222 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0930. Min Act: -0.0001
Data Index: 1336904 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0905. Min Act: -0.0001
Data Index: 75492 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0908. Min Act: -0.0001
Data Index: 400020 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0877. Min Act: -0.0001
Data Index: 1326030 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0821. Min Act: -0.0001
Data Index: 196638 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0867. Min Act: -0.0001
Data Index: 802068 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0890. Min Act: -0.0001
Data Index: 1313356 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0867. Min Act: -0.0001
Data Index: 1050319 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0830. Min Act: -0.0001
Data Index: 106326 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0795. Min Act: -0.0001
Data Index: 685346 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0822. Min Act: -0.0001
Data Index: 894966 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1107. Min Range: -0.1107
Max Act: 0.0786. Min Act: -0.0001
Data Index: 195725 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19