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

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

Neuron 2424 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1543700 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.5838. Min Act: -0.0000

Data Index: 367140 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1226757 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4191. Min Act: -0.0000

Data Index: 739447 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3382. Min Act: -0.0000

Data Index: 634088 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4325. Min Act: -0.0000

Data Index: 924884 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3233. Min Act: -0.0000

Data Index: 342627 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1097040 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3663. Min Act: -0.0000

Data Index: 133685 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1318152 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1145535 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3455. Min Act: -0.0000

Data Index: 187931 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3116. Min Act: 0.0001

Data Index: 273348 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1173026 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3292. Min Act: -0.0000

Data Index: 462662 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1137405 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.2629. Min Act: -0.0000

Data Index: 685613 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3061. Min Act: -0.0000

Data Index: 805257 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.2972. Min Act: -0.0000

Data Index: 722331 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1163973 (C4 (Web Text))

Max Activating Token Index: 708