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

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

Neuron 222 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: 0.4494. Min Range: -0.4494

Max Act: 0.4494. Min Act: -0.0000

Data Index: 514993 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3929. Min Act: -0.0000

Data Index: 608642 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1377776 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1356327 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1095149 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2999. Min Act: -0.0000

Data Index: 28821 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2681. Min Act: -0.0000

Data Index: 952458 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1239998 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2523. Min Act: -0.0000

Data Index: 229794 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2472. Min Act: -0.0000

Data Index: 716909 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1339839 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2309. Min Act: -0.0000

Data Index: 829582 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2383. Min Act: -0.0000

Data Index: 925409 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1057862 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2342. Min Act: -0.0000

Data Index: 20156 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1390726 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1354974 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2064. Min Act: -0.0000

Data Index: 982600 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2223. Min Act: -0.0000

Data Index: 227490 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.2188. Min Act: -0.0000

Data Index: 260998 (C4 (Web Text))

Max Activating Token Index: 424