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

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

Neuron 3418 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: 5.4741. Min Range: -5.4741

Max Act: 5.4741. Min Act: -0.0000

Data Index: 917031 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 5.4741. Min Range: -5.4741

Max Act: 5.1736. Min Act: -0.0000

Data Index: 731772 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 5.4741. Min Range: -5.4741

Max Act: 5.1344. Min Act: -0.0000

Data Index: 436236 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.9419. Min Act: -0.0000

Data Index: 677239 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.5555. Min Act: -0.0000

Data Index: 566111 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.7436. Min Act: -0.0000

Data Index: 1320146 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.8951. Min Act: -0.0000

Data Index: 1030033 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.7034. Min Act: -0.0000

Data Index: 101288 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.6603. Min Act: -0.0000

Data Index: 968943 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.6425. Min Act: -0.0000

Data Index: 984696 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.8372. Min Act: -0.0000

Data Index: 831088 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.6302. Min Act: -0.0000

Data Index: 588367 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.4412. Min Act: -0.0000

Data Index: 1272938 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.6225. Min Act: -0.0000

Data Index: 779705 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.4315. Min Act: -0.0000

Data Index: 378967 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.5979. Min Act: -0.0000

Data Index: 53722 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.5904. Min Act: -0.0000

Data Index: 802720 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.2375. Min Act: -0.0000

Data Index: 734591 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.5631. Min Act: -0.0000

Data Index: 238477 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 5.4741. Min Range: -5.4741

Max Act: 4.3688. Min Act: -0.0000

Data Index: 647272 (C4 (Web Text))

Max Activating Token Index: 193