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

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

Neuron 3154 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: 0.0503. Min Range: -0.0503

Max Act: 0.0502. Min Act: -0.0002

Data Index: 255750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0417. Min Act: -0.0002

Data Index: 488288 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0476. Min Act: -0.0002

Data Index: 396850 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1257991 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0470. Min Act: -0.0002

Data Index: 112258 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1008016 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0440. Min Act: -0.0002

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1344971 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0336. Min Act: -0.0002

Data Index: 38021 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1283159 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1242428 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0378. Min Act: -0.0002

Data Index: 316257 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1051 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0469. Min Act: -0.0002

Data Index: 150222 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1291780 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0427. Min Act: -0.0002

Data Index: 981978 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1029415 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1275922 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1046333 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0400. Min Act: -0.0002

Data Index: 761781 (C4 (Web Text))

Max Activating Token Index: 1023