Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 315 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2927. Min Range: -2.2927
Max Act: 2.2927. Min Act: -0.0001
Data Index: 1271630 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.8330. Min Act: -0.0001
Data Index: 1179983 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.8031. Min Act: -0.0001
Data Index: 302538 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7971. Min Act: -0.0001
Data Index: 596244 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7477. Min Act: -0.0001
Data Index: 316803 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7248. Min Act: -0.0001
Data Index: 330264 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7718. Min Act: -0.0001
Data Index: 85191 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7785. Min Act: -0.0001
Data Index: 40965 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.6518. Min Act: -0.0001
Data Index: 294481 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.6488. Min Act: -0.0001
Data Index: 421138 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.7425. Min Act: -0.0001
Data Index: 1080815 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.5755. Min Act: -0.0001
Data Index: 134266 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.6167. Min Act: -0.0001
Data Index: 565024 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.5936. Min Act: -0.0001
Data Index: 1026190 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.5846. Min Act: -0.0001
Data Index: 823199 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.5012. Min Act: -0.0001
Data Index: 1478330 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.6525. Min Act: -0.0001
Data Index: 290643 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.4735. Min Act: -0.0001
Data Index: 142834 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.4311. Min Act: -0.0001
Data Index: 1619260 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2927. Min Range: -2.2927
Max Act: 1.4755. Min Act: -0.0001
Data Index: 500316 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19