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

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

Neuron 994 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4809. Min Range: -2.4809

Max Act: 2.2757. Min Act: -0.0000

Data Index: 981303 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 2.4809. Min Range: -2.4809

Max Act: 2.4809. Min Act: -0.0000

Data Index: 1175238 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.4809. Min Range: -2.4809

Max Act: 2.1331. Min Act: -0.0000

Data Index: 731543 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.5152. Min Act: -0.0000

Data Index: 279481 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1516587 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.4800. Min Act: -0.0000

Data Index: 25837 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1563848 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1622552 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1378907 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1622489 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1033797 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1581445 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1566619 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1577849 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1401416 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1436612 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1505777 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1552081 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1367046 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 2.4809. Min Range: -2.4809

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1634739 (Python Code)

Max Activating Token Index: 523