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

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

Neuron 2079 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6234. Min Act: -0.0001

Data Index: 77697 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.7675. Min Act: -0.0001

Data Index: 1205821 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.8614. Min Act: -0.0001

Data Index: 296217 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.7382. Min Act: -0.0001

Data Index: 917596 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6836. Min Act: -0.0001

Data Index: 1312119 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.7978. Min Act: -0.0001

Data Index: 329669 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6500. Min Act: -0.0002

Data Index: 823325 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6144. Min Act: -0.0001

Data Index: 1344407 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6786. Min Act: -0.0002

Data Index: 455626 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.5718. Min Act: -0.0001

Data Index: 779191 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6087. Min Act: -0.0001

Data Index: 55455 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.4934. Min Act: -0.0001

Data Index: 277391 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.6587. Min Act: -0.0002

Data Index: 1273996 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.7356. Min Act: -0.0002

Data Index: 390205 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.5599. Min Act: -0.0002

Data Index: 164193 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.7210. Min Act: -0.0002

Data Index: 422602 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.5377. Min Act: -0.0001

Data Index: 666380 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.5715. Min Act: -0.0001

Data Index: 807354 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.3676. Min Act: -0.0001

Data Index: 929987 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.8614. Min Range: -1.8614

Max Act: 1.5056. Min Act: -0.0001

Data Index: 43798 (C4 (Web Text))

Max Activating Token Index: 343