Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2989 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.4044. Min Act: -0.0002

Data Index: 718739 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.3191. Min Act: -0.0002

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2080. Min Act: -0.0002

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1921. Min Act: -0.0002

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2483. Min Act: -0.0002

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2648. Min Act: -0.0002

Data Index: 628354 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1377. Min Act: -0.0002

Data Index: 1215448 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1110. Min Act: -0.0002

Data Index: 333784 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1179. Min Act: -0.0002

Data Index: 1252910 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0371. Min Act: -0.0002

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0590. Min Act: -0.0001

Data Index: 1383868 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0294. Min Act: -0.0002

Data Index: 919346 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9766. Min Act: -0.0002

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0541. Min Act: -0.0002

Data Index: 86010 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9960. Min Act: -0.0001

Data Index: 1441522 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9870. Min Act: -0.0001

Data Index: 809256 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9593. Min Act: -0.0002

Data Index: 1008956 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0176. Min Act: -0.0001

Data Index: 926957 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0067. Min Act: -0.0001

Data Index: 965703 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0020. Min Act: -0.0001

Data Index: 306966 (C4 (Web Text))

Max Activating Token Index: 867