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

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

Neuron 4759 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3576. Min Act: -0.0000

Data Index: 116977 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3594. Min Act: -0.0000

Data Index: 998402 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3172. Min Act: -0.0000

Data Index: 364988 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3359. Min Act: -0.0000

Data Index: 536930 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3332. Min Act: -0.0000

Data Index: 566752 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3117. Min Act: -0.0000

Data Index: 116662 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1233816 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3209. Min Act: -0.0000

Data Index: 905709 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3009. Min Act: -0.0000

Data Index: 709516 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1264879 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2966. Min Act: -0.0000

Data Index: 165237 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2754. Min Act: -0.0000

Data Index: 91441 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2762. Min Act: -0.0000

Data Index: 170708 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2827. Min Act: -0.0000

Data Index: 35087 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3031. Min Act: -0.0000

Data Index: 401540 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2866. Min Act: -0.0000

Data Index: 941518 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2871. Min Act: -0.0000

Data Index: 365359 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2753. Min Act: -0.0000

Data Index: 18724 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.2785. Min Act: -0.0001

Data Index: 368575 (C4 (Web Text))

Max Activating Token Index: 341