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

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

Neuron 3611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0208. Min Range: -2.0208

Max Act: 2.0208. Min Act: -0.0000

Data Index: 739125 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.6272. Min Act: -0.0000

Data Index: 54352 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1072351 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.5673. Min Act: -0.0000

Data Index: 866381 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.4806. Min Act: -0.0000

Data Index: 551073 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.9424. Min Act: -0.0000

Data Index: 192662 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.5396. Min Act: -0.0000

Data Index: 967472 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1042553 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.4265. Min Act: -0.0000

Data Index: 676770 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3976. Min Act: -0.0000

Data Index: 153517 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3770. Min Act: -0.0000

Data Index: 376518 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3675. Min Act: -0.0000

Data Index: 263542 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2734. Min Act: -0.0000

Data Index: 472982 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2658. Min Act: -0.0000

Data Index: 804364 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2583. Min Act: -0.0000

Data Index: 894122 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1064833 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2416. Min Act: -0.0000

Data Index: 795854 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3094. Min Act: -0.0000

Data Index: 334940 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.3701. Min Act: -0.0000

Data Index: 493271 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 2.0208. Min Range: -2.0208

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1155711 (C4 (Web Text))

Max Activating Token Index: 191