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

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

Neuron 2143 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: 0.8403. Min Range: -0.8403

Max Act: 0.8403. Min Act: -0.0001

Data Index: 836688 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.8111. Min Act: -0.0000

Data Index: 358655 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.7545. Min Act: -0.0000

Data Index: 455725 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1291799 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.7654. Min Act: -0.0001

Data Index: 140512 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.7876. Min Act: -0.0001

Data Index: 261313 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.7144. Min Act: -0.0001

Data Index: 498602 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6786. Min Act: -0.0000

Data Index: 757560 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6852. Min Act: -0.0000

Data Index: 887469 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6745. Min Act: -0.0001

Data Index: 37700 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6479. Min Act: -0.0000

Data Index: 311345 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6573. Min Act: -0.0001

Data Index: 514317 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6353. Min Act: -0.0001

Data Index: 931076 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6282. Min Act: -0.0001

Data Index: 250850 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6679. Min Act: -0.0001

Data Index: 941207 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6264. Min Act: -0.0000

Data Index: 317822 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1163266 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.6004. Min Act: -0.0000

Data Index: 362895 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.5902. Min Act: -0.0001

Data Index: 365212 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.8403. Min Range: -0.8403

Max Act: 0.5866. Min Act: -0.0001

Data Index: 223748 (C4 (Web Text))

Max Activating Token Index: 58