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

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

Neuron 4674 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3742. Min Act: -0.0000

Data Index: 592082 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3240. Min Act: -0.0000

Data Index: 717797 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1060346 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3002. Min Act: 0.0000

Data Index: 755376 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.3213. Min Act: -0.0000

Data Index: 492168 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2870. Min Act: 0.0000

Data Index: 499422 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2784. Min Act: -0.0000

Data Index: 309919 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2622. Min Act: -0.0000

Data Index: 393636 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2591. Min Act: -0.0000

Data Index: 808942 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1325411 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2573. Min Act: -0.0000

Data Index: 251170 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2566. Min Act: 0.0001

Data Index: 1206181 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2451. Min Act: -0.0000

Data Index: 611683 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1086602 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1308380 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2474. Min Act: 0.0000

Data Index: 684128 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2436. Min Act: -0.0000

Data Index: 178436 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2409. Min Act: -0.0000

Data Index: 553155 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1154382 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.3742. Min Range: -0.3742

Max Act: 0.2383. Min Act: -0.0000

Data Index: 940690 (C4 (Web Text))

Max Activating Token Index: 343