Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 117 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.5905. Min Act: -0.0001
Data Index: 10612 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4044. Min Act: -0.0001
Data Index: 970009 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4773. Min Act: -0.0001
Data Index: 186254 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4237. Min Act: -0.0001
Data Index: 812322 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4226. Min Act: -0.0001
Data Index: 1132597 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.5306. Min Act: -0.0001
Data Index: 1277072 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4019. Min Act: -0.0001
Data Index: 316283 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4189. Min Act: -0.0001
Data Index: 819719 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4124. Min Act: -0.0001
Data Index: 1359455 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4880. Min Act: -0.0001
Data Index: 48987 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3585. Min Act: -0.0001
Data Index: 1073526 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4125. Min Act: -0.0001
Data Index: 880145 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4914. Min Act: -0.0001
Data Index: 489346 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3216. Min Act: -0.0001
Data Index: 1339841 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.4113. Min Act: -0.0001
Data Index: 275341 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3552. Min Act: -0.0001
Data Index: 424247 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3478. Min Act: -0.0001
Data Index: 111009 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3454. Min Act: -0.0001
Data Index: 541186 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.3463. Min Act: -0.0001
Data Index: 1222823 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5905. Min Range: -1.5905
Max Act: 1.2792. Min Act: -0.0001
Data Index: 925902 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19