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

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

Neuron 3513 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1177065 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1170745 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.2467. Min Act: -0.0001

Data Index: 758419 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0665. Min Act: -0.0001

Data Index: 1330607 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1272785 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0725. Min Act: -0.0000

Data Index: 693368 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0242. Min Act: -0.0000

Data Index: 869638 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9139. Min Act: -0.0000

Data Index: 305763 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0742. Min Act: -0.0001

Data Index: 863068 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.5801. Min Range: -1.5801

Max Act: 1.0262. Min Act: -0.0000

Data Index: 494344 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9675. Min Act: -0.0001

Data Index: 505251 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1205028 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9731. Min Act: -0.0001

Data Index: 18242 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9635. Min Act: -0.0001

Data Index: 114470 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9292. Min Act: -0.0001

Data Index: 19093 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1478400 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1048172 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9130. Min Act: -0.0000

Data Index: 716137 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9075. Min Act: -0.0001

Data Index: 1367784 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 1.5801. Min Range: -1.5801

Max Act: 0.9224. Min Act: -0.0001

Data Index: 470907 (C4 (Web Text))

Max Activating Token Index: 835