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

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

Neuron 2037 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: 1.1816. Min Range: -1.1816

Max Act: 1.1380. Min Act: -0.0000

Data Index: 761243 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.1816. Min Act: -0.0000

Data Index: 869446 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1257082 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1025531 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0865. Min Act: -0.0000

Data Index: 107029 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0827. Min Act: -0.0000

Data Index: 67599 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9756. Min Act: -0.0000

Data Index: 806815 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0084. Min Act: -0.0000

Data Index: 95139 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0876. Min Act: -0.0000

Data Index: 53678 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9387. Min Act: -0.0000

Data Index: 952491 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0216. Min Act: -0.0000

Data Index: 20658 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0148. Min Act: -0.0000

Data Index: 996272 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9710. Min Act: -0.0000

Data Index: 453022 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9907. Min Act: -0.0000

Data Index: 894247 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9678. Min Act: -0.0000

Data Index: 49476 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9665. Min Act: -0.0000

Data Index: 444461 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9603. Min Act: -0.0000

Data Index: 900018 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0183. Min Act: -0.0000

Data Index: 514477 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9726. Min Act: -0.0000

Data Index: 52905 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9740. Min Act: -0.0000

Data Index: 707441 (C4 (Web Text))

Max Activating Token Index: 736