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

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

Neuron 118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.5498. Min Act: -0.0001

Data Index: 502245 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4675. Min Act: -0.0001

Data Index: 920378 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.5396. Min Act: -0.0001

Data Index: 643276 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4780. Min Act: -0.0001

Data Index: 994941 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4451. Min Act: -0.0001

Data Index: 988979 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4329. Min Act: -0.0001

Data Index: 93642 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4609. Min Act: -0.0001

Data Index: 328158 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1105110 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4418. Min Act: -0.0001

Data Index: 160762 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4433. Min Act: -0.0001

Data Index: 170277 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4573. Min Act: -0.0001

Data Index: 741609 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4261. Min Act: -0.0001

Data Index: 649523 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4425. Min Act: -0.0001

Data Index: 1331228 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4339. Min Act: -0.0001

Data Index: 248200 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3929. Min Act: -0.0001

Data Index: 506565 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4032. Min Act: -0.0001

Data Index: 228312 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1275785 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4311. Min Act: -0.0001

Data Index: 767862 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4168. Min Act: -0.0001

Data Index: 975134 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4310. Min Act: -0.0001

Data Index: 15506 (C4 (Web Text))

Max Activating Token Index: 883