Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2799 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.6464. Min Act: -0.0001

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4668. Min Act: -0.0001

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.3859. Min Act: -0.0001

Data Index: 586967 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.0763. Min Act: -0.0001

Data Index: 981997 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.9190. Min Act: -0.0001

Data Index: 893066 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7905. Min Act: -0.0001

Data Index: 522876 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1071347 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8176. Min Act: -0.0001

Data Index: 318243 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8381. Min Act: -0.0001

Data Index: 816466 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1041236 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8150. Min Act: -0.0001

Data Index: 1229067 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7702. Min Act: -0.0001

Data Index: 853001 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7571. Min Act: -0.0001

Data Index: 547452 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7528. Min Act: -0.0001

Data Index: 614826 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7969. Min Act: -0.0001

Data Index: 279855 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1048043 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.6959. Min Act: -0.0001

Data Index: 160228 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7951. Min Act: -0.0001

Data Index: 435603 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.6464. Min Range: -1.6464

Max Act: 0.7843. Min Act: -0.0001

Data Index: 501439 (C4 (Web Text))

Max Activating Token Index: 117