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

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

Neuron 5415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6536. Min Range: -2.6536

Max Act: 2.6536. Min Act: -0.0000

Data Index: 152430 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 2.6536. Min Range: -2.6536

Max Act: 2.0320. Min Act: -0.0000

Data Index: 4791 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.5595. Min Act: -0.0000

Data Index: 851268 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.7743. Min Act: -0.0000

Data Index: 327918 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.5537. Min Act: -0.0000

Data Index: 669932 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.6417. Min Act: -0.0000

Data Index: 1101422 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.5714. Min Act: -0.0000

Data Index: 656690 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.3647. Min Act: -0.0000

Data Index: 3200 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.2598. Min Act: -0.0000

Data Index: 214027 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.3796. Min Act: -0.0000

Data Index: 187920 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.2498. Min Act: -0.0000

Data Index: 28652 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1282352 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.2767. Min Act: -0.0000

Data Index: 514275 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 2.6536. Min Range: -2.6536

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1310659 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1052489 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.1035. Min Act: -0.0000

Data Index: 655729 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.3043. Min Act: -0.0000

Data Index: 202140 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.0152. Min Act: -0.0000

Data Index: 598967 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 2.6536. Min Range: -2.6536

Max Act: 1.0163. Min Act: -0.0000

Data Index: 423984 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 2.6536. Min Range: -2.6536

Max Act: 0.9811. Min Act: -0.0000

Data Index: 549534 (C4 (Web Text))

Max Activating Token Index: 641