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

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

Neuron 2428 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: 4.2334. Min Range: -4.2334

Max Act: 4.2334. Min Act: -0.0000

Data Index: 780234 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.9252. Min Act: -0.0000

Data Index: 1203896 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.6788. Min Act: -0.0000

Data Index: 656586 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.6553. Min Act: -0.0000

Data Index: 951158 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.6529. Min Act: -0.0000

Data Index: 1220299 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.4349. Min Act: -0.0000

Data Index: 313913 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.5692. Min Act: -0.0000

Data Index: 990112 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.8365. Min Act: -0.0000

Data Index: 509562 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.2868. Min Act: -0.0000

Data Index: 1250496 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.0312. Min Act: -0.0000

Data Index: 131665 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.9901. Min Act: -0.0000

Data Index: 840079 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.8614. Min Act: -0.0000

Data Index: 777511 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.9408. Min Act: -0.0000

Data Index: 1149755 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.7596. Min Act: -0.0000

Data Index: 929498 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.5884. Min Act: -0.0000

Data Index: 1030413 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.8529. Min Act: -0.0000

Data Index: 129379 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.1336. Min Act: -0.0000

Data Index: 650765 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.8596. Min Act: -0.0000

Data Index: 948480 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.7169. Min Act: -0.0000

Data Index: 193964 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.5272. Min Act: -0.0000

Data Index: 813559 (C4 (Web Text))

Max Activating Token Index: 319