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

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

Neuron 2138 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1265. Min Range: -3.1265

Max Act: 3.1265. Min Act: -0.0000

Data Index: 388636 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.9926. Min Act: -0.0000

Data Index: 216592 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 3.1265. Min Range: -3.1265

Max Act: 3.1222. Min Act: -0.0000

Data Index: 1097018 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.9480. Min Act: -0.0000

Data Index: 588655 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.9158. Min Act: 0.0000

Data Index: 941731 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.8827. Min Act: -0.0000

Data Index: 699049 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.8260. Min Act: 0.0001

Data Index: 663814 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.7629. Min Act: -0.0000

Data Index: 773098 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.7255. Min Act: 0.0000

Data Index: 414745 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.8608. Min Act: -0.0000

Data Index: 1524844 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.6887. Min Act: -0.0000

Data Index: 201851 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.6663. Min Act: 0.0000

Data Index: 1298191 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.5966. Min Act: -0.0000

Data Index: 1054650 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.7235. Min Act: -0.0000

Data Index: 731319 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.4630. Min Act: -0.0000

Data Index: 33211 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.4274. Min Act: -0.0000

Data Index: 1006381 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1350931 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.4735. Min Act: -0.0000

Data Index: 1116159 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.4648. Min Act: 0.0000

Data Index: 528440 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.1265. Min Range: -3.1265

Max Act: 2.4607. Min Act: -0.0000

Data Index: 355992 (C4 (Web Text))

Max Activating Token Index: 707