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

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

Neuron 1317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.7184. Min Act: -0.0000

Data Index: 882098 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.5710. Min Act: -0.0000

Data Index: 352422 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1331709 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.2910. Min Act: -0.0000

Data Index: 270257 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.1953. Min Act: -0.0000

Data Index: 942358 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.1268. Min Act: -0.0000

Data Index: 503941 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1168100 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.2110. Min Act: -0.0000

Data Index: 392681 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.0368. Min Act: -0.0000

Data Index: 788403 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.0496. Min Act: -0.0000

Data Index: 647487 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1362208 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1533298 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.1089. Min Act: -0.0000

Data Index: 527836 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 1.7184. Min Range: -1.7184

Max Act: 1.0235. Min Act: -0.0000

Data Index: 590411 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9754. Min Act: -0.0000

Data Index: 502137 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9207. Min Act: -0.0000

Data Index: 103570 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9388. Min Act: -0.0000

Data Index: 891415 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9159. Min Act: -0.0000

Data Index: 180255 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1161523 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.7184. Min Range: -1.7184

Max Act: 0.9543. Min Act: -0.0000

Data Index: 411585 (C4 (Web Text))

Max Activating Token Index: 139