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

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

Neuron 661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1098138 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5465. Min Act: -0.0000

Data Index: 67476 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4175. Min Act: -0.0000

Data Index: 77519 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3005. Min Act: -0.0001

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3632. Min Act: -0.0001

Data Index: 113068 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3980. Min Act: -0.0000

Data Index: 802126 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3842. Min Act: -0.0000

Data Index: 589635 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3984. Min Act: -0.0000

Data Index: 352968 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1032116 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1337682 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3583. Min Act: -0.0000

Data Index: 263667 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.2432. Min Act: -0.0001

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3333. Min Act: -0.0000

Data Index: 481295 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1002542 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3458. Min Act: -0.0000

Data Index: 275665 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3061. Min Act: -0.0000

Data Index: 227542 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3251. Min Act: -0.0000

Data Index: 195732 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3137. Min Act: -0.0000

Data Index: 680610 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3187. Min Act: -0.0000

Data Index: 654493 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.2909. Min Act: -0.0001

Data Index: 633451 (C4 (Web Text))

Max Activating Token Index: 809