Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1248. Min Range: -1.1248

Max Act: 1.0539. Min Act: -0.0001

Data Index: 734227 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.1248. Min Range: -1.1248

Max Act: 1.1248. Min Act: -0.0001

Data Index: 548291 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.1248. Min Range: -1.1248

Max Act: 1.0777. Min Act: -0.0001

Data Index: 170399 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.1248. Min Range: -1.1248

Max Act: 1.0351. Min Act: -0.0001

Data Index: 1021790 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.1248. Min Range: -1.1248

Max Act: 1.0336. Min Act: -0.0001

Data Index: 898051 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9430. Min Act: -0.0001

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9416. Min Act: -0.0001

Data Index: 604993 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9655. Min Act: -0.0001

Data Index: 973261 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1254667 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9342. Min Act: -0.0001

Data Index: 251615 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9427. Min Act: -0.0001

Data Index: 788145 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9144. Min Act: -0.0000

Data Index: 526176 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1263627 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1322236 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8923. Min Act: -0.0001

Data Index: 577987 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8899. Min Act: -0.0001

Data Index: 187118 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1030932 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8700. Min Act: -0.0001

Data Index: 28172 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1106737 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.1248. Min Range: -1.1248

Max Act: 0.8281. Min Act: -0.0001

Data Index: 867206 (C4 (Web Text))

Max Activating Token Index: 782