Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2140 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0522. Min Act: -0.0001
Data Index: 824924 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0528. Min Act: -0.0001
Data Index: 974353 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0502. Min Act: -0.0001
Data Index: 1290000 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0454. Min Act: -0.0001
Data Index: 262113 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0474. Min Act: -0.0001
Data Index: 800857 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0451. Min Act: -0.0001
Data Index: 367708 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0482. Min Act: -0.0001
Data Index: 716659 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0465. Min Act: -0.0001
Data Index: 870593 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0453. Min Act: -0.0001
Data Index: 467656 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0465. Min Act: -0.0001
Data Index: 27744 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0471. Min Act: -0.0001
Data Index: 298507 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0434. Min Act: -0.0001
Data Index: 780966 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0438. Min Act: -0.0001
Data Index: 106060 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0427. Min Act: -0.0001
Data Index: 1334552 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0426. Min Act: -0.0001
Data Index: 546169 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0438. Min Act: -0.0001
Data Index: 1549399 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0460. Min Act: -0.0001
Data Index: 1553480 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0433. Min Act: -0.0001
Data Index: 805491 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0423. Min Act: -0.0001
Data Index: 326999 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0528. Min Range: -0.0528
Max Act: 0.0412. Min Act: -0.0001
Data Index: 1511288 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19