Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3992 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3079. Min Act: -0.0000

Data Index: 508665 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3118. Min Act: -0.0000

Data Index: 792858 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1273898 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2748. Min Act: -0.0000

Data Index: 530057 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2745. Min Act: -0.0000

Data Index: 130431 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2400. Min Act: -0.0000

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2512. Min Act: -0.0000

Data Index: 231339 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2517. Min Act: -0.0000

Data Index: 518463 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2578. Min Act: -0.0000

Data Index: 986780 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2432. Min Act: -0.0000

Data Index: 616869 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2522. Min Act: -0.0000

Data Index: 19514 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2426. Min Act: -0.0000

Data Index: 662780 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2525. Min Act: -0.0000

Data Index: 488170 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2468. Min Act: -0.0000

Data Index: 385342 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1007062 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1342988 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1333382 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1185888 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1018985 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1350567 (C4 (Web Text))

Max Activating Token Index: 773