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

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

Neuron 2343 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: 2.2660. Min Range: -2.2660

Max Act: 2.1646. Min Act: -0.0000

Data Index: 651783 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.2660. Min Act: -0.0000

Data Index: 648833 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.2568. Min Act: -0.0000

Data Index: 1168929 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.1795. Min Act: -0.0000

Data Index: 393333 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.0219. Min Act: -0.0000

Data Index: 970637 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.1500. Min Act: -0.0000

Data Index: 925422 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.0567. Min Act: -0.0000

Data Index: 83193 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 2.2660. Min Range: -2.2660

Max Act: 2.0204. Min Act: -0.0000

Data Index: 592503 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.9391. Min Act: -0.0000

Data Index: 628411 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.8095. Min Act: -0.0000

Data Index: 551749 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.6401. Min Act: -0.0000

Data Index: 694183 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.3484. Min Act: -0.0000

Data Index: 741509 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.7850. Min Act: -0.0000

Data Index: 756842 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.6389. Min Act: -0.0000

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.6113. Min Act: -0.0000

Data Index: 741448 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.7541. Min Act: -0.0000

Data Index: 544829 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1080782 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.6143. Min Act: -0.0000

Data Index: 536504 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 2.2660. Min Range: -2.2660

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1138371 (C4 (Web Text))

Max Activating Token Index: 234