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

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

Neuron 1043 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0416. Min Range: -1.0416

Max Act: 1.0416. Min Act: -0.0002

Data Index: 204776 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.0416. Min Range: -1.0416

Max Act: 1.0268. Min Act: -0.0002

Data Index: 838474 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9494. Min Act: -0.0002

Data Index: 383718 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.7446. Min Act: -0.0002

Data Index: 1208320 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9531. Min Act: -0.0002

Data Index: 448615 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9435. Min Act: -0.0002

Data Index: 956214 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9401. Min Act: -0.0002

Data Index: 265826 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8880. Min Act: -0.0002

Data Index: 755631 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9168. Min Act: -0.0002

Data Index: 503001 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9257. Min Act: -0.0002

Data Index: 720151 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9253. Min Act: -0.0002

Data Index: 1101916 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.7891. Min Act: -0.0002

Data Index: 663328 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8285. Min Act: -0.0002

Data Index: 506675 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8356. Min Act: -0.0002

Data Index: 189300 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8662. Min Act: -0.0002

Data Index: 789610 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.9405. Min Act: -0.0002

Data Index: 8460 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8307. Min Act: -0.0002

Data Index: 1256928 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.7657. Min Act: -0.0002

Data Index: 331341 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.7695. Min Act: -0.0002

Data Index: 253063 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.0416. Min Range: -1.0416

Max Act: 0.8910. Min Act: -0.0002

Data Index: 1352700 (C4 (Web Text))

Max Activating Token Index: 198