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

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

Neuron 3165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.7190. Min Act: -0.0001

Data Index: 259467 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.6146. Min Act: -0.0001

Data Index: 1273178 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.5742. Min Act: -0.0001

Data Index: 722208 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.6124. Min Act: -0.0001

Data Index: 672852 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.5649. Min Act: -0.0001

Data Index: 475622 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.4736. Min Act: -0.0001

Data Index: 504316 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.3602. Min Act: -0.0001

Data Index: 1288190 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.3618. Min Act: -0.0001

Data Index: 595378 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.3546. Min Act: -0.0001

Data Index: 225354 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2911. Min Act: -0.0001

Data Index: 28221 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2735. Min Act: -0.0001

Data Index: 1202008 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2771. Min Act: -0.0001

Data Index: 188224 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.3124. Min Act: -0.0001

Data Index: 1107045 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1009383 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2164. Min Act: -0.0001

Data Index: 486572 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2410. Min Act: -0.0001

Data Index: 1261386 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2390. Min Act: -0.0001

Data Index: 1357451 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.1879. Min Act: -0.0001

Data Index: 1052123 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.1116. Min Act: -0.0001

Data Index: 782509 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.7190. Min Range: -1.7190

Max Act: 1.2156. Min Act: -0.0001

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 458