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

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

Neuron 1618 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: 1.2316. Min Range: -1.2316

Max Act: 1.1974. Min Act: -0.0000

Data Index: 670148 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.2311. Min Act: -0.0000

Data Index: 215130 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.2316. Min Act: -0.0000

Data Index: 301222 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.1634. Min Act: -0.0000

Data Index: 889761 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.1182. Min Act: -0.0000

Data Index: 604310 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1306060 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1289628 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0554. Min Act: -0.0000

Data Index: 615027 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9806. Min Act: -0.0000

Data Index: 113177 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0329. Min Act: -0.0000

Data Index: 947419 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9510. Min Act: -0.0000

Data Index: 47397 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0035. Min Act: -0.0000

Data Index: 394674 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9940. Min Act: 0.0000

Data Index: 1326190 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9933. Min Act: -0.0000

Data Index: 196896 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9842. Min Act: -0.0000

Data Index: 683399 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9842. Min Act: -0.0000

Data Index: 637237 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 1.2316. Min Range: -1.2316

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1307593 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9039. Min Act: -0.0000

Data Index: 731383 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9576. Min Act: -0.0000

Data Index: 666232 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.2316. Min Range: -1.2316

Max Act: 0.9549. Min Act: -0.0000

Data Index: 14797 (C4 (Web Text))

Max Activating Token Index: 794