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

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

Neuron 1678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3708. Min Act: -0.0001

Data Index: 1613560 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3263. Min Act: -0.0001

Data Index: 933519 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1390387 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2899. Min Act: -0.0001

Data Index: 623830 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1350361 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2807. Min Act: -0.0001

Data Index: 661410 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1276437 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3250. Min Act: -0.0001

Data Index: 73741 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2944. Min Act: -0.0001

Data Index: 617704 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2736. Min Act: -0.0001

Data Index: 921041 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1029473 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1292106 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2481. Min Act: -0.0001

Data Index: 300606 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3226. Min Act: -0.0001

Data Index: 1489558 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1612113 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2661. Min Act: -0.0001

Data Index: 322987 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3036. Min Act: -0.0001

Data Index: 559491 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3007. Min Act: -0.0001

Data Index: 940620 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2840. Min Act: -0.0001

Data Index: 215290 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1007409 (C4 (Web Text))

Max Activating Token Index: 225