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

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

Neuron 843 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.6038. Min Act: -0.0000

Data Index: 180416 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.3198. Min Act: -0.0001

Data Index: 986731 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.1585. Min Act: -0.0001

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.1813. Min Act: -0.0001

Data Index: 993071 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0270. Min Act: -0.0001

Data Index: 1075034 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0126. Min Act: -0.0001

Data Index: 861945 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0269. Min Act: -0.0001

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0316. Min Act: -0.0001

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.3264. Min Act: -0.0001

Data Index: 717416 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.6038. Min Range: -3.6038

Max Act: 2.9864. Min Act: -0.0001

Data Index: 55338 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 3.6038. Min Range: -3.6038

Max Act: 2.9228. Min Act: -0.0000

Data Index: 502106 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 3.6038. Min Range: -3.6038

Max Act: 2.9043. Min Act: -0.0001

Data Index: 196645 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.1916. Min Act: -0.0001

Data Index: 590098 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0267. Min Act: -0.0000

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0287. Min Act: -0.0001

Data Index: 1265594 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0376. Min Act: -0.0001

Data Index: 885417 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0534. Min Act: -0.0001

Data Index: 872514 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 3.6038. Min Range: -3.6038

Max Act: 2.8562. Min Act: -0.0001

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 3.6038. Min Range: -3.6038

Max Act: 2.8609. Min Act: -0.0001

Data Index: 666309 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.6038. Min Range: -3.6038

Max Act: 3.0104. Min Act: -0.0000

Data Index: 663887 (C4 (Web Text))

Max Activating Token Index: 188