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

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

Neuron 5153 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1100199 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1485387 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0832. Min Act: -0.0000

Data Index: 310994 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1166605 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9486. Min Act: -0.0000

Data Index: 890970 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9573. Min Act: -0.0000

Data Index: 536781 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1408983 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9421. Min Act: -0.0000

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9472. Min Act: -0.0000

Data Index: 286241 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1247904 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1130048 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9332. Min Act: -0.0000

Data Index: 596984 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.1642. Min Range: -1.1642

Max Act: 1.0388. Min Act: -0.0000

Data Index: 121356 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1107578 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8805. Min Act: -0.0000

Data Index: 290948 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8445. Min Act: -0.0000

Data Index: 359448 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8182. Min Act: -0.0000

Data Index: 973441 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.9028. Min Act: -0.0000

Data Index: 191349 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8747. Min Act: -0.0000

Data Index: 204905 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.1642. Min Range: -1.1642

Max Act: 0.8658. Min Act: -0.0000

Data Index: 890616 (C4 (Web Text))

Max Activating Token Index: 212