Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1541 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.4343. Min Act: -0.0000

Data Index: 737438 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3649. Min Act: -0.0000

Data Index: 590196 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3744. Min Act: -0.0000

Data Index: 347959 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3287. Min Act: -0.0000

Data Index: 966014 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3257. Min Act: -0.0000

Data Index: 672134 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3332. Min Act: -0.0001

Data Index: 21157 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3258. Min Act: -0.0000

Data Index: 949813 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3108. Min Act: -0.0000

Data Index: 893475 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3096. Min Act: -0.0000

Data Index: 323666 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3424. Min Act: -0.0001

Data Index: 671390 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2889. Min Act: -0.0001

Data Index: 831678 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3321. Min Act: -0.0000

Data Index: 535244 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2855. Min Act: -0.0001

Data Index: 778108 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3152. Min Act: -0.0000

Data Index: 639509 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1156918 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3179. Min Act: -0.0000

Data Index: 954943 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1004249 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.2668. Min Act: -0.0000

Data Index: 918379 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1102760 (C4 (Web Text))

Max Activating Token Index: 1011