Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 28 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.7288. Min Act: -0.0001
Data Index: 113023 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.8307. Min Act: -0.0001
Data Index: 24308 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.7198. Min Act: -0.0001
Data Index: 535817 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.8244. Min Act: -0.0001
Data Index: 728403 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.4435. Min Act: -0.0001
Data Index: 78425 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.4979. Min Act: -0.0001
Data Index: 1121929 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.4860. Min Act: -0.0001
Data Index: 1273167 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.6094. Min Act: -0.0001
Data Index: 505310 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.5806. Min Act: -0.0001
Data Index: 567732 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.4048. Min Act: -0.0001
Data Index: 99871 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.2666. Min Act: -0.0001
Data Index: 1122450 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.6175. Min Act: -0.0001
Data Index: 233682 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.2459. Min Act: -0.0001
Data Index: 875686 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.2435. Min Act: -0.0001
Data Index: 706558 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.3101. Min Act: -0.0001
Data Index: 1046266 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.2964. Min Act: -0.0001
Data Index: 291303 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.3640. Min Act: -0.0001
Data Index: 562849 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.1569. Min Act: -0.0001
Data Index: 1154620 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.1089. Min Act: -0.0001
Data Index: 364599 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8307. Min Range: -2.8307
Max Act: 2.1063. Min Act: -0.0001
Data Index: 1052495 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19