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

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

Neuron 3794 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: 0.4757. Min Range: -0.4757

Max Act: 0.4757. Min Act: -0.0001

Data Index: 1146556 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4714. Min Act: -0.0001

Data Index: 105943 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4250. Min Act: -0.0001

Data Index: 1344724 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4067. Min Act: -0.0000

Data Index: 441632 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1248194 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3636. Min Act: -0.0001

Data Index: 1150060 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3431. Min Act: -0.0001

Data Index: 120674 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3158. Min Act: -0.0001

Data Index: 247337 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3262. Min Act: -0.0001

Data Index: 391014 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3160. Min Act: -0.0001

Data Index: 1029467 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2966. Min Act: -0.0000

Data Index: 338532 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2871. Min Act: -0.0001

Data Index: 183142 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2845. Min Act: -0.0000

Data Index: 945561 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1186887 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1271800 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2688. Min Act: -0.0001

Data Index: 725462 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2799. Min Act: -0.0000

Data Index: 336999 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1321306 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2731. Min Act: -0.0001

Data Index: 288388 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2497. Min Act: -0.0001

Data Index: 511272 (C4 (Web Text))

Max Activating Token Index: 871