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

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

Neuron 3773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3157. Min Range: -4.3157

Max Act: 4.3064. Min Act: -0.0000

Data Index: 1273775 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 4.3157. Min Range: -4.3157

Max Act: 4.3157. Min Act: -0.0000

Data Index: 99516 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9610. Min Act: -0.0000

Data Index: 1207409 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.9217. Min Act: -0.0000

Data Index: 354772 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.5860. Min Act: -0.0000

Data Index: 244693 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.5581. Min Act: -0.0000

Data Index: 822757 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.5039. Min Act: -0.0000

Data Index: 1329792 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1315730 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.5067. Min Act: -0.0000

Data Index: 211308 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.6828. Min Act: -0.0000

Data Index: 528436 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.4706. Min Act: -0.0000

Data Index: 38291 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.4584. Min Act: -0.0000

Data Index: 650483 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.1465. Min Act: -0.0000

Data Index: 99825 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.5498. Min Act: -0.0000

Data Index: 1328131 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.1769. Min Act: -0.0000

Data Index: 1305087 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.1905. Min Act: -0.0000

Data Index: 1273909 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.3191. Min Act: -0.0000

Data Index: 328250 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.0291. Min Act: -0.0000

Data Index: 679080 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.0384. Min Act: -0.0000

Data Index: 222454 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 4.3157. Min Range: -4.3157

Max Act: 3.3208. Min Act: -0.0000

Data Index: 1151844 (C4 (Web Text))

Max Activating Token Index: 603