Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2746 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1465911 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1545923 (Python Code)

Max Activating Token Index: 691

Text #2

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1553501 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1384771 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1033312 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.1884. Min Act: -0.0000

Data Index: 68461 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0370. Min Act: 0.0000

Data Index: 530028 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1152852 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.9890. Min Act: -0.0000

Data Index: 972853 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1543516 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0092. Min Act: -0.0000

Data Index: 792728 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0015. Min Act: -0.0000

Data Index: 17462 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1186751 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1066424 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1534168 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 1.2575. Min Range: -1.2575

Max Act: 1.0059. Min Act: -0.0000

Data Index: 878677 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.9139. Min Act: -0.0000

Data Index: 864355 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.7927. Min Act: 0.0000

Data Index: 1193616 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1091007 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.2575. Min Range: -1.2575

Max Act: 0.9158. Min Act: -0.0000

Data Index: 835006 (C4 (Web Text))

Max Activating Token Index: 846