Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1336674 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3466. Min Act: -0.0000

Data Index: 126049 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3237. Min Act: -0.0001

Data Index: 667085 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3018. Min Act: -0.0001

Data Index: 517621 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2965. Min Act: -0.0001

Data Index: 476968 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2746. Min Act: -0.0001

Data Index: 179235 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1252377 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2611. Min Act: -0.0001

Data Index: 866509 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2468. Min Act: -0.0001

Data Index: 988450 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2569. Min Act: -0.0001

Data Index: 926039 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2571. Min Act: -0.0001

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2501. Min Act: -0.0001

Data Index: 702258 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2507. Min Act: -0.0000

Data Index: 851417 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2428. Min Act: -0.0001

Data Index: 406346 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2446. Min Act: -0.0000

Data Index: 247661 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2595. Min Act: -0.0001

Data Index: 261295 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2318. Min Act: -0.0001

Data Index: 111657 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1034551 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2398. Min Act: -0.0000

Data Index: 442882 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1175752 (C4 (Web Text))

Max Activating Token Index: 878