Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1572 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.8696. Min Act: -0.0002
Data Index: 728536 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.8535. Min Act: -0.0001
Data Index: 1357990 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.8121. Min Act: -0.0001
Data Index: 460733 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.7911. Min Act: -0.0002
Data Index: 680144 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.7308. Min Act: -0.0001
Data Index: 74246 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.7129. Min Act: -0.0001
Data Index: 584961 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.8482. Min Act: -0.0002
Data Index: 1222924 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6896. Min Act: -0.0002
Data Index: 1151330 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.7548. Min Act: -0.0001
Data Index: 325768 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.7076. Min Act: -0.0001
Data Index: 892408 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6820. Min Act: -0.0001
Data Index: 396143 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.5106. Min Act: -0.0001
Data Index: 126073 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6852. Min Act: -0.0002
Data Index: 1011296 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6447. Min Act: -0.0001
Data Index: 260439 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6344. Min Act: -0.0002
Data Index: 977581 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.6768. Min Act: -0.0001
Data Index: 262220 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.5839. Min Act: -0.0001
Data Index: 1287473 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.5929. Min Act: -0.0001
Data Index: 508591 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.5241. Min Act: -0.0002
Data Index: 999843 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8696. Min Range: -1.8696
Max Act: 1.5126. Min Act: -0.0001
Data Index: 1208686 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19