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

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

Neuron 4806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.3478. Min Act: -0.0000

Data Index: 6020 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.3638. Min Act: -0.0000

Data Index: 807739 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1245416 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.3140. Min Act: -0.0000

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1437756 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1551643 (Python Code)

Max Activating Token Index: 903

Text #7

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1547780 (Python Code)

Max Activating Token Index: 708

Text #8

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1488617 (Python Code)

Max Activating Token Index: 1013

Text #9

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1368066 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1409655 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1464315 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2425. Min Act: -0.0000

Data Index: 727751 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2323. Min Act: -0.0000

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1639357 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1632262 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1575789 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2389. Min Act: -0.0000

Data Index: 254022 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1489397 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 0.3638. Min Range: -0.3638

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1581636 (Python Code)

Max Activating Token Index: 510