Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2717 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0004

Data Index: 584860 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1275568 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0513. Min Act: -0.0003

Data Index: 675259 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0508. Min Act: -0.0003

Data Index: 383414 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0484. Min Act: -0.0004

Data Index: 15825 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0500. Min Act: -0.0003

Data Index: 739118 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0490. Min Act: -0.0003

Data Index: 757163 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0447. Min Act: -0.0003

Data Index: 147425 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1325325 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0439. Min Act: -0.0003

Data Index: 880465 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0418. Min Act: -0.0004

Data Index: 350841 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0450. Min Act: -0.0003

Data Index: 295222 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0446. Min Act: -0.0003

Data Index: 596634 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1112868 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0460. Min Act: -0.0003

Data Index: 97588 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1168615 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0437. Min Act: -0.0003

Data Index: 953392 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0420. Min Act: -0.0003

Data Index: 142934 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0421. Min Act: -0.0003

Data Index: 943074 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1325967 (C4 (Web Text))

Max Activating Token Index: 993