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

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

Neuron 4760 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.9662. Min Act: -0.0000

Data Index: 84874 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.6337. Min Act: -0.0000

Data Index: 524638 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4877. Min Act: -0.0000

Data Index: 440417 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.2796. Min Act: -0.0000

Data Index: 113344 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.3277. Min Act: -0.0000

Data Index: 167443 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1557. Min Act: -0.0000

Data Index: 759139 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1943. Min Act: -0.0000

Data Index: 995959 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1845. Min Act: -0.0001

Data Index: 342543 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1293482 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.2356. Min Act: -0.0000

Data Index: 404485 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1084256 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1176. Min Act: -0.0000

Data Index: 332400 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1292. Min Act: -0.0000

Data Index: 814485 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1034497 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1283. Min Act: -0.0000

Data Index: 144431 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.1241. Min Act: -0.0000

Data Index: 596101 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.9662. Min Range: -1.9662

Max Act: 0.9599. Min Act: -0.0001

Data Index: 808765 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.0320. Min Act: -0.0001

Data Index: 697079 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1314293 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.0735. Min Act: -0.0000

Data Index: 612222 (C4 (Web Text))

Max Activating Token Index: 462