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

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

Neuron 229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.5189. Min Act: -0.0001

Data Index: 542433 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4399. Min Act: -0.0001

Data Index: 1082626 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3920. Min Act: -0.0001

Data Index: 605964 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4142. Min Act: -0.0001

Data Index: 658836 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3512. Min Act: -0.0001

Data Index: 1195589 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4060. Min Act: -0.0001

Data Index: 232248 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3458. Min Act: -0.0001

Data Index: 1279675 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.2985. Min Act: -0.0001

Data Index: 11416 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4039. Min Act: -0.0001

Data Index: 565075 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.2925. Min Act: -0.0001

Data Index: 233130 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3229. Min Act: -0.0001

Data Index: 275595 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1029348 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3020. Min Act: -0.0001

Data Index: 639566 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4940. Min Act: -0.0001

Data Index: 607397 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.2521. Min Act: -0.0001

Data Index: 1028131 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.4193. Min Act: -0.0001

Data Index: 57272 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3142. Min Act: -0.0001

Data Index: 31005 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.3508. Min Act: -0.0001

Data Index: 820267 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.2976. Min Act: -0.0001

Data Index: 187510 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.5189. Min Range: -1.5189

Max Act: 1.2929. Min Act: -0.0001

Data Index: 953526 (C4 (Web Text))

Max Activating Token Index: 717