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

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

Neuron 2691 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: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1292311 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5032. Min Act: -0.0000

Data Index: 739023 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5318. Min Act: -0.0000

Data Index: 562152 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4858. Min Act: -0.0000

Data Index: 77389 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5264. Min Act: -0.0000

Data Index: 226896 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5103. Min Act: -0.0000

Data Index: 816724 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1321406 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4473. Min Act: -0.0000

Data Index: 86507 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1119041 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1001637 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4218. Min Act: -0.0000

Data Index: 522291 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4256. Min Act: -0.0000

Data Index: 43742 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1276834 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1229481 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4160. Min Act: -0.0000

Data Index: 917430 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3968. Min Act: -0.0000

Data Index: 958167 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4017. Min Act: -0.0000

Data Index: 682010 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1339952 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4246. Min Act: -0.0000

Data Index: 420437 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1016591 (C4 (Web Text))

Max Activating Token Index: 698