Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1014 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0003

Data Index: 501061 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0716. Min Act: -0.0003

Data Index: 463800 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0666. Min Act: -0.0003

Data Index: 989604 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0627. Min Act: -0.0003

Data Index: 928736 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0576. Min Act: -0.0004

Data Index: 713496 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0567. Min Act: -0.0003

Data Index: 670489 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0562. Min Act: -0.0003

Data Index: 846092 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1143185 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0546. Min Act: -0.0003

Data Index: 945556 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0576. Min Act: -0.0002

Data Index: 998407 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0544. Min Act: -0.0001

Data Index: 497375 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0530. Min Act: -0.0002

Data Index: 138148 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1229088 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1375 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0517. Min Act: -0.0002

Data Index: 135236 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0527. Min Act: -0.0004

Data Index: 653576 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0517. Min Act: -0.0003

Data Index: 103247 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0527. Min Act: -0.0003

Data Index: 392040 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1264228 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0511. Min Act: -0.0002

Data Index: 434195 (C4 (Web Text))

Max Activating Token Index: 354