Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1288 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2447. Min Range: -2.2447

Max Act: 2.2447. Min Act: -0.0001

Data Index: 172894 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 2.2447. Min Range: -2.2447

Max Act: 2.1590. Min Act: -0.0001

Data Index: 314056 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 2.2447. Min Range: -2.2447

Max Act: 2.0799. Min Act: -0.0001

Data Index: 277736 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.9501. Min Act: -0.0000

Data Index: 1253008 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 2.2447. Min Range: -2.2447

Max Act: 2.0031. Min Act: -0.0001

Data Index: 96923 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.9266. Min Act: -0.0000

Data Index: 1176736 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.9218. Min Act: -0.0000

Data Index: 909770 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7082. Min Act: -0.0001

Data Index: 1020885 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.6967. Min Act: -0.0001

Data Index: 1299828 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7817. Min Act: -0.0000

Data Index: 605879 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1299444 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7344. Min Act: -0.0000

Data Index: 1183894 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.8183. Min Act: -0.0001

Data Index: 79885 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.6927. Min Act: -0.0000

Data Index: 644807 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7743. Min Act: -0.0000

Data Index: 82447 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.7597. Min Act: -0.0001

Data Index: 1271281 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.6397. Min Act: -0.0000

Data Index: 220924 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.5943. Min Act: -0.0000

Data Index: 313054 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.5453. Min Act: -0.0000

Data Index: 247476 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 2.2447. Min Range: -2.2447

Max Act: 1.4557. Min Act: -0.0000

Data Index: 191957 (C4 (Web Text))

Max Activating Token Index: 761