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

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

Neuron 588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0000

Data Index: 916303 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0766. Min Act: -0.0001

Data Index: 740214 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0654. Min Act: -0.0001

Data Index: 679767 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0652. Min Act: -0.0000

Data Index: 956065 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1138056 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0657. Min Act: -0.0001

Data Index: 627646 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0676. Min Act: -0.0001

Data Index: 267571 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1265699 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0638. Min Act: -0.0000

Data Index: 958312 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1397910 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0591. Min Act: -0.0001

Data Index: 222530 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0604. Min Act: -0.0001

Data Index: 580288 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0613. Min Act: -0.0001

Data Index: 310132 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0602. Min Act: -0.0001

Data Index: 856370 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0570. Min Act: -0.0001

Data Index: 520305 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0629. Min Act: -0.0001

Data Index: 461589 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0601. Min Act: -0.0001

Data Index: 306137 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0603. Min Act: -0.0001

Data Index: 200321 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1264592 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1131344 (C4 (Web Text))

Max Activating Token Index: 526