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

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

Neuron 3359 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6376. Min Range: -3.6376

Max Act: 3.6376. Min Act: -0.0000

Data Index: 1108567 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 3.6376. Min Range: -3.6376

Max Act: 3.4156. Min Act: -0.0000

Data Index: 727444 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.6376. Min Range: -3.6376

Max Act: 3.1857. Min Act: -0.0000

Data Index: 882254 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.7145. Min Act: -0.0000

Data Index: 932722 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.8785. Min Act: -0.0000

Data Index: 1295699 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.8691. Min Act: -0.0000

Data Index: 368510 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.8157. Min Act: -0.0000

Data Index: 410744 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6427. Min Act: -0.0000

Data Index: 338991 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6859. Min Act: -0.0000

Data Index: 433730 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6695. Min Act: -0.0000

Data Index: 1222507 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.7970. Min Act: -0.0000

Data Index: 1248307 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6088. Min Act: -0.0000

Data Index: 194838 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6766. Min Act: -0.0000

Data Index: 193121 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.5158. Min Act: -0.0000

Data Index: 153654 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.5152. Min Act: -0.0000

Data Index: 387042 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.6488. Min Act: -0.0000

Data Index: 1094647 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.4785. Min Act: -0.0000

Data Index: 1186373 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.3507. Min Act: -0.0000

Data Index: 851753 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.3338. Min Act: -0.0000

Data Index: 145638 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.6376. Min Range: -3.6376

Max Act: 2.5899. Min Act: -0.0000

Data Index: 1292319 (C4 (Web Text))

Max Activating Token Index: 669