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

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

Neuron 5380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6358. Min Range: -2.6358

Max Act: 2.4421. Min Act: -0.0000

Data Index: 977891 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 2.6358. Min Range: -2.6358

Max Act: 2.6358. Min Act: -0.0000

Data Index: 1031069 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.6487. Min Act: -0.0000

Data Index: 288082 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.7224. Min Act: -0.0000

Data Index: 1031386 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1124203 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.6205. Min Act: -0.0000

Data Index: 824695 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1323674 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.6963. Min Act: -0.0000

Data Index: 923516 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.4636. Min Act: -0.0000

Data Index: 60863 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1186768 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1100995 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.3946. Min Act: -0.0000

Data Index: 727942 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.1986. Min Act: -0.0000

Data Index: 117438 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.3685. Min Act: -0.0000

Data Index: 866491 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.4160. Min Act: -0.0000

Data Index: 365174 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.4195. Min Act: -0.0000

Data Index: 363990 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.4873. Min Act: -0.0000

Data Index: 153116 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.3076. Min Act: -0.0000

Data Index: 646870 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.3711. Min Act: -0.0000

Data Index: 378942 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 2.6358. Min Range: -2.6358

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1350864 (C4 (Web Text))

Max Activating Token Index: 154