Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3614 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.2561. Min Act: -0.0001
Data Index: 227006 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.3722. Min Act: -0.0001
Data Index: 1060950 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.1499. Min Act: -0.0001
Data Index: 871437 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.2629. Min Act: -0.0001
Data Index: 1000931 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8390. Min Act: -0.0001
Data Index: 279237 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.1513. Min Act: -0.0001
Data Index: 913624 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7588. Min Act: -0.0001
Data Index: 366079 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8844. Min Act: -0.0001
Data Index: 1206080 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8719. Min Act: -0.0001
Data Index: 26961 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8897. Min Act: -0.0001
Data Index: 355855 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.0287. Min Act: -0.0001
Data Index: 75920 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.5387. Min Act: -0.0001
Data Index: 809429 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8070. Min Act: -0.0001
Data Index: 934303 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8112. Min Act: -0.0001
Data Index: 209276 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9541. Min Act: -0.0001
Data Index: 271033 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7852. Min Act: -0.0001
Data Index: 904592 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.5865. Min Act: -0.0001
Data Index: 1346034 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7839. Min Act: -0.0001
Data Index: 316351 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7514. Min Act: -0.0001
Data Index: 1187446 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7198. Min Act: -0.0001
Data Index: 173101 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19