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

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

Neuron 1228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1997 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3828. Min Act: -0.0000

Data Index: 139946 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1038220 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2897. Min Act: -0.0000

Data Index: 813254 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1299711 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2753. Min Act: -0.0000

Data Index: 347477 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2778. Min Act: -0.0000

Data Index: 742428 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1296616 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2553. Min Act: -0.0000

Data Index: 57030 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2556. Min Act: -0.0000

Data Index: 380832 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2631. Min Act: -0.0000

Data Index: 688284 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2953. Min Act: -0.0000

Data Index: 70954 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2516. Min Act: -0.0000

Data Index: 134263 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2526. Min Act: -0.0000

Data Index: 9936 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2511. Min Act: -0.0000

Data Index: 960662 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1270179 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2404. Min Act: -0.0000

Data Index: 648492 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1060324 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2433. Min Act: -0.0000

Data Index: 850737 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1211693 (C4 (Web Text))

Max Activating Token Index: 398