Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3969. Min Act: -0.0001

Data Index: 489958 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.3004. Min Act: -0.0001

Data Index: 570768 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.2959. Min Act: -0.0001

Data Index: 380048 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.2769. Min Act: -0.0001

Data Index: 355304 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1258. Min Act: -0.0001

Data Index: 1197986 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0277. Min Act: -0.0001

Data Index: 965070 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1421. Min Act: -0.0001

Data Index: 133461 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0642. Min Act: -0.0001

Data Index: 650256 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0946. Min Act: -0.0001

Data Index: 133836 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0023. Min Act: -0.0001

Data Index: 5032 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.1280. Min Act: -0.0001

Data Index: 1120928 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.9823. Min Act: -0.0001

Data Index: 109461 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0228. Min Act: -0.0001

Data Index: 671760 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.9332. Min Act: -0.0001

Data Index: 847207 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.9557. Min Act: -0.0001

Data Index: 955814 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0788. Min Act: -0.0001

Data Index: 439251 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.8928. Min Act: -0.0001

Data Index: 1196309 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.3969. Min Range: -1.3969

Max Act: 1.0107. Min Act: -0.0001

Data Index: 655300 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.9161. Min Act: -0.0001

Data Index: 27471 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.3969. Min Range: -1.3969

Max Act: 0.8889. Min Act: -0.0001

Data Index: 971106 (C4 (Web Text))

Max Activating Token Index: 326