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

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

Neuron 100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5978. Min Act: -0.0001

Data Index: 439882 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5705. Min Act: -0.0000

Data Index: 163304 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5796. Min Act: -0.0000

Data Index: 223178 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5533. Min Act: -0.0001

Data Index: 1189170 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5157. Min Act: -0.0001

Data Index: 744843 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1066718 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5022. Min Act: 0.0000

Data Index: 1301168 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4767. Min Act: -0.0000

Data Index: 917119 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4736. Min Act: -0.0001

Data Index: 897395 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1014901 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4867. Min Act: 0.0000

Data Index: 1104180 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4644. Min Act: 0.0000

Data Index: 627778 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4636. Min Act: -0.0000

Data Index: 341645 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1132436 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4892. Min Act: -0.0001

Data Index: 460326 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5035. Min Act: -0.0000

Data Index: 990510 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4857. Min Act: -0.0000

Data Index: 954982 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4237. Min Act: -0.0001

Data Index: 1225078 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4606. Min Act: -0.0000

Data Index: 397968 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4587. Min Act: -0.0001

Data Index: 440392 (C4 (Web Text))

Max Activating Token Index: 999