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

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

Neuron 2000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1028303 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0550. Min Act: -0.0002

Data Index: 520221 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0503. Min Act: -0.0002

Data Index: 355718 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0469. Min Act: -0.0002

Data Index: 991161 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0464. Min Act: -0.0002

Data Index: 211126 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0466. Min Act: -0.0002

Data Index: 879712 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0477. Min Act: -0.0002

Data Index: 544797 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0460. Min Act: -0.0002

Data Index: 627717 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0433. Min Act: -0.0002

Data Index: 904132 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0447. Min Act: -0.0002

Data Index: 381985 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1160887 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0433. Min Act: -0.0002

Data Index: 38280 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0411. Min Act: -0.0002

Data Index: 825781 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0418. Min Act: -0.0002

Data Index: 163641 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0419. Min Act: -0.0002

Data Index: 610416 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1101403 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1222134 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0418. Min Act: -0.0002

Data Index: 699515 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1121684 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0402. Min Act: -0.0002

Data Index: 689995 (C4 (Web Text))

Max Activating Token Index: 516