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

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

Neuron 1830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1175450 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6355. Min Act: -0.0000

Data Index: 541371 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6314. Min Act: -0.0000

Data Index: 158813 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6286. Min Act: -0.0000

Data Index: 976367 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6492. Min Act: -0.0000

Data Index: 2002 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1340978 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5662. Min Act: -0.0000

Data Index: 267902 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1275387 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5671. Min Act: -0.0000

Data Index: 761215 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4983. Min Act: -0.0000

Data Index: 249196 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5003. Min Act: -0.0000

Data Index: 580799 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5351. Min Act: -0.0000

Data Index: 716464 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1275998 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4670. Min Act: -0.0000

Data Index: 77754 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5201. Min Act: -0.0000

Data Index: 713217 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5339. Min Act: -0.0000

Data Index: 383373 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5207. Min Act: -0.0000

Data Index: 479675 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5193. Min Act: -0.0000

Data Index: 153659 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1285055 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1219494 (C4 (Web Text))

Max Activating Token Index: 454