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

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

Neuron 383 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: 2.0549. Min Range: -2.0549

Max Act: 2.0549. Min Act: -0.0000

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.7361. Min Act: -0.0000

Data Index: 872807 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1001394 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.5988. Min Act: -0.0000

Data Index: 3108 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.5428. Min Act: -0.0000

Data Index: 223694 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.6234. Min Act: -0.0000

Data Index: 934187 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1033351 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4839. Min Act: -0.0000

Data Index: 891843 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1128909 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1643777 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4554. Min Act: -0.0000

Data Index: 829723 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4372. Min Act: -0.0000

Data Index: 174730 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4487. Min Act: -0.0000

Data Index: 88235 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4308. Min Act: -0.0000

Data Index: 829628 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.2240. Min Act: -0.0000

Data Index: 108658 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1478015 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.4618. Min Act: -0.0000

Data Index: 787061 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.3890. Min Act: -0.0000

Data Index: 247975 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 2.0549. Min Range: -2.0549

Max Act: 1.3755. Min Act: -0.0000

Data Index: 312098 (C4 (Web Text))

Max Activating Token Index: 1003