Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2528 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8742. Min Range: -2.8742

Max Act: 2.8742. Min Act: -0.0000

Data Index: 954669 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 2.8742. Min Range: -2.8742

Max Act: 2.2206. Min Act: -0.0000

Data Index: 797583 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.8314. Min Act: -0.0000

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6334. Min Act: -0.0000

Data Index: 614386 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6901. Min Act: -0.0000

Data Index: 990944 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1044301 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6696. Min Act: -0.0000

Data Index: 491556 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.7434. Min Act: -0.0000

Data Index: 597477 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6417. Min Act: -0.0000

Data Index: 1576687 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.5460. Min Act: -0.0000

Data Index: 1145140 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6129. Min Act: -0.0000

Data Index: 666275 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.5828. Min Act: -0.0000

Data Index: 393963 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1307633 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1307922 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1114754 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1074464 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.6053. Min Act: -0.0000

Data Index: 717153 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.4979. Min Act: -0.0000

Data Index: 892523 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.4867. Min Act: -0.0000

Data Index: 317692 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 2.8742. Min Range: -2.8742

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1009828 (C4 (Web Text))

Max Activating Token Index: 488