Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1017 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1304850 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6311. Min Act: -0.0000

Data Index: 430124 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5441. Min Act: -0.0000

Data Index: 865581 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1038884 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5071. Min Act: -0.0000

Data Index: 849325 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4562. Min Act: -0.0000

Data Index: 724754 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4808. Min Act: -0.0000

Data Index: 689232 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1230275 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4361. Min Act: -0.0000

Data Index: 983256 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1120035 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1160424 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4401. Min Act: -0.0000

Data Index: 769213 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4191. Min Act: -0.0000

Data Index: 126285 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4310. Min Act: -0.0000

Data Index: 594603 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4099. Min Act: -0.0000

Data Index: 817764 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1321754 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1201539 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.3077. Min Act: -0.0000

Data Index: 279065 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4263. Min Act: -0.0000

Data Index: 578693 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1204085 (C4 (Web Text))

Max Activating Token Index: 618