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

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

Neuron 4666 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9384. Min Range: -3.9384

Max Act: 3.9384. Min Act: -0.0000

Data Index: 1291882 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.9384. Min Range: -3.9384

Max Act: 3.6755. Min Act: -0.0000

Data Index: 783108 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.7918. Min Act: -0.0000

Data Index: 920012 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.7279. Min Act: -0.0000

Data Index: 490844 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.5236. Min Act: -0.0000

Data Index: 1238500 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1311478 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.3545. Min Act: -0.0000

Data Index: 1232438 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.3778. Min Act: -0.0000

Data Index: 29778 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.5265. Min Act: -0.0000

Data Index: 1089803 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.3736. Min Act: -0.0000

Data Index: 293241 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.2167. Min Act: -0.0000

Data Index: 52496 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.2975. Min Act: -0.0000

Data Index: 252480 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.3914. Min Act: -0.0000

Data Index: 1188363 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.2368. Min Act: -0.0000

Data Index: 244916 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.3352. Min Act: -0.0000

Data Index: 1170483 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.2065. Min Act: -0.0000

Data Index: 473687 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.1948. Min Act: -0.0000

Data Index: 293297 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.0726. Min Act: -0.0000

Data Index: 741206 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.0756. Min Act: -0.0000

Data Index: 1097232 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 3.9384. Min Range: -3.9384

Max Act: 2.0761. Min Act: -0.0000

Data Index: 713861 (C4 (Web Text))

Max Activating Token Index: 161