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

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

Neuron 3413 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: 1.5063. Min Range: -1.5063

Max Act: 1.5063. Min Act: -0.0001

Data Index: 1015684 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.3343. Min Act: -0.0000

Data Index: 432924 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.3223. Min Act: -0.0000

Data Index: 319565 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2446. Min Act: -0.0001

Data Index: 1026023 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2881. Min Act: -0.0001

Data Index: 1184406 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.3134. Min Act: -0.0001

Data Index: 759492 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2907. Min Act: -0.0001

Data Index: 724998 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2082. Min Act: -0.0001

Data Index: 930158 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2368. Min Act: -0.0001

Data Index: 271286 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1787. Min Act: -0.0001

Data Index: 278592 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2173. Min Act: -0.0001

Data Index: 103677 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0647. Min Act: -0.0001

Data Index: 910872 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0702. Min Act: -0.0001

Data Index: 765150 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1323. Min Act: -0.0001

Data Index: 288200 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1228538 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0673. Min Act: -0.0001

Data Index: 1190076 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0208. Min Act: -0.0001

Data Index: 232678 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0893. Min Act: -0.0001

Data Index: 450312 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0511. Min Act: -0.0000

Data Index: 53244 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0180. Min Act: -0.0001

Data Index: 191366 (C4 (Web Text))

Max Activating Token Index: 546