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

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

Neuron 3396 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.7530. Min Act: -0.0000

Data Index: 525822 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.6671. Min Act: -0.0000

Data Index: 849139 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.5745. Min Act: -0.0000

Data Index: 712797 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.5098. Min Act: -0.0000

Data Index: 622169 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.6070. Min Act: -0.0000

Data Index: 917323 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.4496. Min Act: -0.0000

Data Index: 1357617 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.5707. Min Act: -0.0000

Data Index: 578392 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.5255. Min Act: -0.0000

Data Index: 25117 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.6463. Min Act: -0.0000

Data Index: 924997 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.4162. Min Act: -0.0000

Data Index: 945027 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.6566. Min Act: -0.0000

Data Index: 818138 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.2641. Min Act: -0.0000

Data Index: 1053327 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.3303. Min Act: -0.0000

Data Index: 509157 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.3050. Min Act: -0.0000

Data Index: 799286 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.2531. Min Act: -0.0000

Data Index: 721271 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.2460. Min Act: -0.0000

Data Index: 359692 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.2416. Min Act: -0.0000

Data Index: 898271 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.3368. Min Act: -0.0000

Data Index: 1001698 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.0793. Min Act: -0.0000

Data Index: 632960 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 2.7530. Min Range: -2.7530

Max Act: 2.2616. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 638