Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 165 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.7182. Min Act: -0.0002

Data Index: 613898 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1068452 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6595. Min Act: -0.0001

Data Index: 512910 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1280468 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1098563 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6197. Min Act: -0.0001

Data Index: 536512 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6190. Min Act: -0.0001

Data Index: 374113 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1308044 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6230. Min Act: -0.0001

Data Index: 254748 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6085. Min Act: -0.0001

Data Index: 782965 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6704. Min Act: -0.0001

Data Index: 408223 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6144. Min Act: -0.0001

Data Index: 951397 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5508. Min Act: -0.0001

Data Index: 899245 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6683. Min Act: -0.0001

Data Index: 100969 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1354128 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5521. Min Act: -0.0001

Data Index: 1055265 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6046. Min Act: -0.0001

Data Index: 984211 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5818. Min Act: -0.0001

Data Index: 463933 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5872. Min Act: -0.0001

Data Index: 25925 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.6575. Min Act: -0.0001

Data Index: 22543 (C4 (Web Text))

Max Activating Token Index: 1009