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

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

Neuron 2022 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.1324. Min Act: -0.0000

Data Index: 318624 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0067. Min Act: -0.0000

Data Index: 798230 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0227. Min Act: 0.0000

Data Index: 106784 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9441. Min Act: 0.0001

Data Index: 440934 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8950. Min Act: 0.0000

Data Index: 64712 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8971. Min Act: 0.0001

Data Index: 884970 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8758. Min Act: 0.0001

Data Index: 165081 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8516. Min Act: 0.0000

Data Index: 174158 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1136841 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7868. Min Act: 0.0001

Data Index: 743486 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8238. Min Act: 0.0001

Data Index: 869411 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1229439 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7902. Min Act: 0.0001

Data Index: 933148 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7800. Min Act: 0.0001

Data Index: 609902 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7584. Min Act: 0.0000

Data Index: 940348 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7517. Min Act: -0.0000

Data Index: 238464 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1141796 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7482. Min Act: 0.0001

Data Index: 331339 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7511. Min Act: 0.0000

Data Index: 140002 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.6842. Min Act: 0.0000

Data Index: 746701 (C4 (Web Text))

Max Activating Token Index: 128