Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5675 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1156735 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.7584. Min Act: -0.0000

Data Index: 19890 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5918. Min Act: 0.0000

Data Index: 465090 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5401. Min Act: -0.0000

Data Index: 404720 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5442. Min Act: 0.0000

Data Index: 207691 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5340. Min Act: -0.0000

Data Index: 751056 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5519. Min Act: -0.0000

Data Index: 993834 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5250. Min Act: -0.0000

Data Index: 457601 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5242. Min Act: -0.0000

Data Index: 523796 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5063. Min Act: -0.0000

Data Index: 569171 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4925. Min Act: -0.0000

Data Index: 282452 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1143983 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5254. Min Act: -0.0000

Data Index: 516738 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4974. Min Act: -0.0000

Data Index: 200002 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1032594 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4837. Min Act: -0.0000

Data Index: 712089 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4895. Min Act: -0.0000

Data Index: 541051 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4868. Min Act: 0.0000

Data Index: 164986 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.4725. Min Act: -0.0000

Data Index: 712273 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.8383. Min Range: -0.8383

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1041139 (C4 (Web Text))

Max Activating Token Index: 646