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

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

Neuron 3713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4398. Min Act: -0.0003

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.8339. Min Act: -0.0003

Data Index: 810892 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.5205. Min Act: -0.0003

Data Index: 1162241 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3324. Min Act: -0.0003

Data Index: 1247352 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.7338. Min Act: -0.0003

Data Index: 327831 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.5124. Min Act: -0.0003

Data Index: 1040668 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4516. Min Act: -0.0003

Data Index: 1213788 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4521. Min Act: -0.0003

Data Index: 685873 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1321. Min Act: -0.0003

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.5952. Min Act: -0.0003

Data Index: 269856 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1094. Min Act: -0.0003

Data Index: 1193588 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1423. Min Act: -0.0003

Data Index: 590235 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.5514. Min Act: -0.0003

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3061. Min Act: -0.0003

Data Index: 123812 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3726. Min Act: -0.0003

Data Index: 727190 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4890. Min Act: -0.0003

Data Index: 1245572 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4158. Min Act: -0.0003

Data Index: 1133907 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1346. Min Act: -0.0003

Data Index: 33660 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1953. Min Act: -0.0003

Data Index: 23870 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3740. Min Act: -0.0003

Data Index: 402608 (C4 (Web Text))

Max Activating Token Index: 730