Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 54 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.0362. Min Range: -3.0362
Max Act: 3.0362. Min Act: -0.0001
Data Index: 292204 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.9373. Min Act: -0.0001
Data Index: 331990 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.7553. Min Act: -0.0001
Data Index: 92107 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4664. Min Act: -0.0001
Data Index: 1152575 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.6075. Min Act: -0.0001
Data Index: 877077 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4714. Min Act: -0.0001
Data Index: 1332125 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.2459. Min Act: -0.0001
Data Index: 1291719 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.5687. Min Act: -0.0001
Data Index: 1243707 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4213. Min Act: -0.0001
Data Index: 1299139 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.2112. Min Act: -0.0001
Data Index: 336129 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4204. Min Act: -0.0001
Data Index: 848859 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.1565. Min Act: -0.0001
Data Index: 223874 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.2869. Min Act: -0.0001
Data Index: 621110 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4763. Min Act: -0.0001
Data Index: 868001 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.1136. Min Act: -0.0001
Data Index: 1278178 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.3413. Min Act: -0.0001
Data Index: 767841 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.2265. Min Act: -0.0001
Data Index: 38413 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.4317. Min Act: -0.0001
Data Index: 900780 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.3143. Min Act: -0.0001
Data Index: 256404 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0362. Min Range: -3.0362
Max Act: 2.2699. Min Act: -0.0001
Data Index: 1042827 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19