Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2720 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.6250. Min Act: -0.0001
Data Index: 973899 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.6205. Min Act: -0.0001
Data Index: 1019026 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.2029. Min Act: -0.0001
Data Index: 1346311 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.1964. Min Act: -0.0001
Data Index: 1204651 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.2909. Min Act: -0.0001
Data Index: 1334407 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.4704. Min Act: -0.0001
Data Index: 201093 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.4555. Min Act: -0.0001
Data Index: 1250446 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.3064. Min Act: -0.0001
Data Index: 473766 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.2716. Min Act: -0.0001
Data Index: 830234 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.2873. Min Act: -0.0001
Data Index: 1332130 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.1706. Min Act: -0.0001
Data Index: 1187034 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0592. Min Act: -0.0001
Data Index: 1244215 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.1371. Min Act: -0.0001
Data Index: 934282 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.4344. Min Act: -0.0001
Data Index: 1053030 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6250. Min Range: -2.6250
Max Act: 1.9948. Min Act: -0.0001
Data Index: 1306509 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0382. Min Act: -0.0001
Data Index: 1355222 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0279. Min Act: -0.0001
Data Index: 161818 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0192. Min Act: -0.0001
Data Index: 365589 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0062. Min Act: -0.0001
Data Index: 1035626 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6250. Min Range: -2.6250
Max Act: 2.0078. Min Act: -0.0001
Data Index: 699664 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19