Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3335 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7818. Min Act: -0.0001
Data Index: 57646 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7613. Min Act: -0.0001
Data Index: 587115 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7615. Min Act: -0.0001
Data Index: 96131 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7445. Min Act: -0.0001
Data Index: 806931 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7795. Min Act: -0.0001
Data Index: 933134 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7261. Min Act: -0.0001
Data Index: 137281 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7477. Min Act: -0.0001
Data Index: 9647 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7451. Min Act: -0.0001
Data Index: 819651 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7393. Min Act: -0.0001
Data Index: 125515 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7611. Min Act: -0.0001
Data Index: 933452 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7541. Min Act: -0.0001
Data Index: 333119 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7113. Min Act: -0.0001
Data Index: 12528 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7500. Min Act: -0.0001
Data Index: 1073318 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7546. Min Act: -0.0001
Data Index: 233880 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.6639. Min Act: -0.0001
Data Index: 504839 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7216. Min Act: -0.0001
Data Index: 891469 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7430. Min Act: -0.0001
Data Index: 975378 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7235. Min Act: -0.0001
Data Index: 1166969 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7406. Min Act: -0.0001
Data Index: 536406 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7818. Min Range: -0.7818
Max Act: 0.7029. Min Act: -0.0001
Data Index: 656123 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19