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

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

Neuron 3776 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: 0.4720. Min Range: -0.4720

Max Act: 0.4720. Min Act: 0.0000

Data Index: 1295768 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1647626 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1474062 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1260663 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1499643 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3668. Min Act: 0.0000

Data Index: 1024478 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3620. Min Act: -0.0000

Data Index: 903216 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1543676 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1520080 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1078284 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3625. Min Act: 0.0000

Data Index: 1336594 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1494022 (Python Code)

Max Activating Token Index: 604

Text #12

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1437585 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1498869 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1582768 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1558824 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1144057 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1364141 (Python Code)

Max Activating Token Index: 862

Text #18

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3171. Min Act: 0.0000

Data Index: 425717 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1363443 (Python Code)

Max Activating Token Index: 596