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

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

Neuron 4042 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8398. Min Act: -0.0001

Data Index: 339290 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7240. Min Act: -0.0001

Data Index: 1163168 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8062. Min Act: -0.0001

Data Index: 1322356 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7570. Min Act: -0.0001

Data Index: 269622 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.8491. Min Act: -0.0001

Data Index: 1262149 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7667. Min Act: -0.0000

Data Index: 641354 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7223. Min Act: -0.0001

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1012004 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7526. Min Act: -0.0001

Data Index: 681781 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7476. Min Act: -0.0001

Data Index: 605695 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7364. Min Act: -0.0000

Data Index: 522458 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6845. Min Act: -0.0001

Data Index: 478942 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1265871 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6553. Min Act: -0.0000

Data Index: 216514 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1144752 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6781. Min Act: -0.0001

Data Index: 992118 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6602. Min Act: -0.0001

Data Index: 108801 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6475. Min Act: -0.0001

Data Index: 20498 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6425. Min Act: -0.0001

Data Index: 529233 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.8491. Min Range: -0.8491

Max Act: 0.6407. Min Act: -0.0001

Data Index: 1275952 (C4 (Web Text))

Max Activating Token Index: 94