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

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

Neuron 86 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3920. Min Act: -0.0000

Data Index: 994050 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3204. Min Act: -0.0000

Data Index: 890783 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.4318. Min Act: -0.0000

Data Index: 450933 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1291504 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3582. Min Act: -0.0000

Data Index: 761047 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2280. Min Act: -0.0000

Data Index: 308857 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2207. Min Act: -0.0000

Data Index: 718502 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.3107. Min Act: -0.0000

Data Index: 780898 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2246. Min Act: -0.0000

Data Index: 873260 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.1868. Min Act: -0.0000

Data Index: 627490 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1171032 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.1421. Min Act: -0.0000

Data Index: 314032 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0588. Min Act: -0.0000

Data Index: 929328 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.1260. Min Act: -0.0000

Data Index: 370401 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.4318. Min Range: -1.4318

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1023741 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0943. Min Act: -0.0000

Data Index: 23059 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1325371 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0780. Min Act: -0.0000

Data Index: 157072 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.0313. Min Act: -0.0000

Data Index: 488416 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.4318. Min Range: -1.4318

Max Act: 1.1201. Min Act: -0.0000

Data Index: 434075 (C4 (Web Text))

Max Activating Token Index: 618