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

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

Neuron 2002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.8162. Min Act: -0.0001

Data Index: 199568 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.8243. Min Act: -0.0000

Data Index: 1020928 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7657. Min Act: -0.0001

Data Index: 126793 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7545. Min Act: -0.0001

Data Index: 737021 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6160. Min Act: -0.0001

Data Index: 1034107 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5852. Min Act: -0.0001

Data Index: 977910 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7622. Min Act: -0.0001

Data Index: 233336 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5522. Min Act: -0.0001

Data Index: 1111332 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5434. Min Act: -0.0001

Data Index: 477455 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6233. Min Act: -0.0001

Data Index: 1004187 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6205. Min Act: -0.0000

Data Index: 837211 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6050. Min Act: -0.0000

Data Index: 689964 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5957. Min Act: -0.0000

Data Index: 766094 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5744. Min Act: -0.0001

Data Index: 185024 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1023091 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5547. Min Act: -0.0001

Data Index: 1261505 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4514. Min Act: -0.0001

Data Index: 176577 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6191. Min Act: -0.0001

Data Index: 433796 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5279. Min Act: -0.0001

Data Index: 1333397 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4541. Min Act: -0.0001

Data Index: 399675 (C4 (Web Text))

Max Activating Token Index: 859