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

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

Neuron 2402 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.5088. Min Act: -0.0001

Data Index: 36555 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.0854. Min Act: -0.0001

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.9844. Min Act: -0.0001

Data Index: 1000054 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.7988. Min Act: -0.0001

Data Index: 1030512 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.0336. Min Act: -0.0001

Data Index: 1253453 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.8751. Min Act: -0.0001

Data Index: 1064640 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.6064. Min Act: -0.0001

Data Index: 1060040 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5693. Min Act: -0.0001

Data Index: 1096814 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.6238. Min Act: -0.0001

Data Index: 441754 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.4818. Min Act: -0.0001

Data Index: 284130 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5628. Min Act: -0.0001

Data Index: 403004 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5575. Min Act: -0.0001

Data Index: 386549 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.4920. Min Act: -0.0001

Data Index: 602052 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3800. Min Act: -0.0001

Data Index: 197640 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5963. Min Act: -0.0001

Data Index: 1015653 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3000. Min Act: -0.0001

Data Index: 1207068 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3945. Min Act: -0.0001

Data Index: 827176 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.1692. Min Act: -0.0001

Data Index: 541790 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.2669. Min Act: -0.0001

Data Index: 588816 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.2722. Min Act: -0.0001

Data Index: 405470 (C4 (Web Text))

Max Activating Token Index: 582