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

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

Neuron 2532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4353. Min Act: -0.0001

Data Index: 306384 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4260. Min Act: -0.0001

Data Index: 241167 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1010086 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3805. Min Act: -0.0001

Data Index: 1031710 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1112018 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3395. Min Act: -0.0001

Data Index: 132832 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1231716 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3473. Min Act: -0.0001

Data Index: 659885 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3526. Min Act: -0.0001

Data Index: 1254489 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3419. Min Act: -0.0001

Data Index: 591607 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3412. Min Act: -0.0001

Data Index: 765798 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3705. Min Act: -0.0001

Data Index: 571380 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3366. Min Act: -0.0001

Data Index: 572352 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3229. Min Act: -0.0001

Data Index: 483709 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3328. Min Act: -0.0001

Data Index: 820237 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3427. Min Act: -0.0001

Data Index: 745021 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3275. Min Act: -0.0001

Data Index: 193902 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3133. Min Act: -0.0001

Data Index: 945482 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3237. Min Act: -0.0001

Data Index: 793971 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3229. Min Act: -0.0001

Data Index: 307127 (C4 (Web Text))

Max Activating Token Index: 34