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

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

Neuron 4552 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.7911. Min Act: -0.0001

Data Index: 251510 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.8493. Min Act: -0.0001

Data Index: 944924 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.5590. Min Act: -0.0001

Data Index: 516983 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.3106. Min Act: -0.0001

Data Index: 814801 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.4059. Min Act: -0.0001

Data Index: 220957 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.9493. Min Act: -0.0000

Data Index: 14112 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.5221. Min Act: -0.0001

Data Index: 72115 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.6616. Min Act: -0.0001

Data Index: 823592 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3675. Min Act: -0.0000

Data Index: 838285 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.1059. Min Act: -0.0001

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3531. Min Act: -0.0001

Data Index: 891089 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.2241. Min Act: -0.0001

Data Index: 87459 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3127. Min Act: -0.0001

Data Index: 1229174 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.1472. Min Act: -0.0001

Data Index: 1354368 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.4945. Min Act: -0.0000

Data Index: 950093 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3575. Min Act: -0.0001

Data Index: 212522 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.6310. Min Act: -0.0001

Data Index: 532943 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.8254. Min Act: -0.0001

Data Index: 459896 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.7915. Min Act: -0.0000

Data Index: 349129 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.9661. Min Act: -0.0001

Data Index: 754712 (C4 (Web Text))

Max Activating Token Index: 178