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

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

Neuron 3207 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: 0.4635. Min Range: -0.4635

Max Act: 0.4563. Min Act: -0.0000

Data Index: 178950 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4428. Min Act: -0.0000

Data Index: 953168 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4635. Min Act: -0.0000

Data Index: 50431 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4366. Min Act: -0.0000

Data Index: 993796 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1072109 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3552. Min Act: -0.0000

Data Index: 602730 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3642. Min Act: -0.0000

Data Index: 529583 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1560625 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1237621 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3334. Min Act: -0.0000

Data Index: 903591 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3108. Min Act: -0.0000

Data Index: 447707 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3328. Min Act: -0.0000

Data Index: 909967 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1090442 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3201. Min Act: -0.0000

Data Index: 367376 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3234. Min Act: -0.0000

Data Index: 161622 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3307. Min Act: -0.0000

Data Index: 966686 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1350632 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3268. Min Act: -0.0000

Data Index: 609889 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3457. Min Act: -0.0000

Data Index: 564416 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1227049 (C4 (Web Text))

Max Activating Token Index: 624