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

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

Neuron 713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1060026 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0354. Min Act: -0.0002

Data Index: 678671 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0332. Min Act: -0.0003

Data Index: 253023 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0322. Min Act: -0.0003

Data Index: 831177 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0339. Min Act: -0.0003

Data Index: 256666 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0303. Min Act: -0.0002

Data Index: 217945 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0326. Min Act: -0.0002

Data Index: 275405 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1000228 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1214408 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0329. Min Act: -0.0002

Data Index: 757137 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0302. Min Act: -0.0002

Data Index: 280665 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1204090 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0315. Min Act: -0.0002

Data Index: 419023 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0315. Min Act: -0.0002

Data Index: 35423 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0300. Min Act: -0.0002

Data Index: 871265 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0289. Min Act: -0.0003

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0303. Min Act: -0.0002

Data Index: 141466 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0298. Min Act: -0.0003

Data Index: 902743 (C4 (Web Text))

Max Activating Token Index: 921