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

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

Neuron 2391 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: 1.4975. Min Range: -1.4975

Max Act: 1.4975. Min Act: -0.0002

Data Index: 1071986 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3595. Min Act: -0.0002

Data Index: 381384 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0799. Min Act: -0.0002

Data Index: 728278 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0999. Min Act: -0.0002

Data Index: 724898 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0438. Min Act: -0.0002

Data Index: 1012384 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9944. Min Act: -0.0002

Data Index: 194574 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0138. Min Act: -0.0002

Data Index: 93509 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0505. Min Act: -0.0002

Data Index: 334481 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0342. Min Act: -0.0002

Data Index: 968956 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9536. Min Act: -0.0002

Data Index: 1181224 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.8771. Min Act: -0.0002

Data Index: 841241 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.8895. Min Act: -0.0002

Data Index: 799781 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9710. Min Act: -0.0002

Data Index: 670479 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9221. Min Act: -0.0002

Data Index: 1070515 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9798. Min Act: -0.0002

Data Index: 68095 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9168. Min Act: -0.0002

Data Index: 354063 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9306. Min Act: -0.0002

Data Index: 1071461 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9629. Min Act: -0.0002

Data Index: 939435 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.8972. Min Act: -0.0002

Data Index: 1089378 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9051. Min Act: -0.0002

Data Index: 518889 (C4 (Web Text))

Max Activating Token Index: 378