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

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

Neuron 5930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.8943. Min Act: -0.0000

Data Index: 1288822 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.4583. Min Act: -0.0000

Data Index: 335338 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.8729. Min Act: -0.0000

Data Index: 95342 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.4172. Min Act: -0.0000

Data Index: 835413 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.4063. Min Act: -0.0000

Data Index: 126058 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.3609. Min Act: -0.0000

Data Index: 859001 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.3440. Min Act: -0.0000

Data Index: 765398 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.2745. Min Act: -0.0000

Data Index: 862023 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.2640. Min Act: -0.0000

Data Index: 1123458 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.2762. Min Act: -0.0000

Data Index: 1277980 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1256. Min Act: -0.0000

Data Index: 1271097 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1407. Min Act: 0.0000

Data Index: 23421 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.2037. Min Act: 0.0000

Data Index: 894026 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1601. Min Act: -0.0000

Data Index: 512603 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1237. Min Act: -0.0000

Data Index: 13678 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.8943. Min Range: -2.8943

Max Act: 1.9883. Min Act: -0.0000

Data Index: 353953 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1051. Min Act: -0.0000

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1805. Min Act: -0.0000

Data Index: 117580 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.0538. Min Act: -0.0000

Data Index: 908318 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 2.8943. Min Range: -2.8943

Max Act: 2.1736. Min Act: -0.0000

Data Index: 445920 (C4 (Web Text))

Max Activating Token Index: 328