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

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

Neuron 4682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.6708. Min Act: -0.0002

Data Index: 182215 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.5221. Min Act: -0.0002

Data Index: 285835 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.5990. Min Act: -0.0002

Data Index: 175363 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4746. Min Act: -0.0002

Data Index: 1083069 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.5534. Min Act: -0.0002

Data Index: 394859 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4628. Min Act: -0.0002

Data Index: 850183 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3942. Min Act: -0.0002

Data Index: 888875 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4818. Min Act: -0.0002

Data Index: 875469 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.5528. Min Act: -0.0002

Data Index: 1320705 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3678. Min Act: -0.0002

Data Index: 480132 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4267. Min Act: -0.0002

Data Index: 1090116 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4154. Min Act: -0.0002

Data Index: 889385 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4067. Min Act: -0.0002

Data Index: 991628 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.2850. Min Act: -0.0002

Data Index: 1063296 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3119. Min Act: -0.0002

Data Index: 1110911 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3377. Min Act: -0.0002

Data Index: 976712 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3497. Min Act: -0.0002

Data Index: 212663 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.4485. Min Act: -0.0002

Data Index: 1318061 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.3295. Min Act: -0.0002

Data Index: 368104 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.6708. Min Range: -1.6708

Max Act: 1.2754. Min Act: -0.0002

Data Index: 1212088 (C4 (Web Text))

Max Activating Token Index: 345