Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2659 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0002. Min Range: -1.0002

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1144108 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8438. Min Act: -0.0000

Data Index: 440796 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1339514 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8026. Min Act: -0.0000

Data Index: 177452 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7546. Min Act: -0.0000

Data Index: 75722 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1246425 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6468. Min Act: -0.0000

Data Index: 228752 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1149369 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6258. Min Act: -0.0000

Data Index: 799863 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1288137 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1208262 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1209108 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6070. Min Act: -0.0000

Data Index: 920292 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5820. Min Act: -0.0000

Data Index: 839624 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5407. Min Act: -0.0000

Data Index: 815432 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5963. Min Act: -0.0000

Data Index: 19530 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5945. Min Act: -0.0000

Data Index: 300206 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5170. Min Act: -0.0000

Data Index: 512774 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1121028 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1365882 (Python Code)

Max Activating Token Index: 769