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

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

Neuron 1380 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.6287. Min Act: -0.0000

Data Index: 571541 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.3525. Min Act: -0.0000

Data Index: 209800 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.2233. Min Act: -0.0000

Data Index: 28679 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1156861 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1092665 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1326449 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.1480. Min Act: -0.0000

Data Index: 490468 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0505. Min Act: -0.0000

Data Index: 772225 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0235. Min Act: -0.0000

Data Index: 306069 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1075000 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0250. Min Act: -0.0000

Data Index: 455585 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0536. Min Act: -0.0000

Data Index: 833181 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0511. Min Act: -0.0000

Data Index: 531108 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9698. Min Act: -0.0000

Data Index: 758333 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1098068 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9762. Min Act: -0.0000

Data Index: 318481 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1184255 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9163. Min Act: -0.0000

Data Index: 795257 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8831. Min Act: -0.0000

Data Index: 273331 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8921. Min Act: -0.0000

Data Index: 335911 (C4 (Web Text))

Max Activating Token Index: 592