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

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

Neuron 1052 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0467. Min Range: -5.0467

Max Act: 5.0467. Min Act: -0.0000

Data Index: 1153452 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.7921. Min Act: -0.0000

Data Index: 390383 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.1915. Min Act: -0.0000

Data Index: 1119428 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.0060. Min Act: -0.0000

Data Index: 885136 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.9693. Min Act: -0.0000

Data Index: 41898 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.4678. Min Act: -0.0000

Data Index: 1042030 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.4004. Min Act: -0.0000

Data Index: 1317590 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.9961. Min Act: -0.0000

Data Index: 20374 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.6223. Min Act: -0.0000

Data Index: 245947 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.7286. Min Act: -0.0000

Data Index: 1065515 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.4644. Min Act: -0.0000

Data Index: 997515 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.6303. Min Act: -0.0000

Data Index: 441535 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.3686. Min Act: -0.0000

Data Index: 219862 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.6481. Min Act: -0.0000

Data Index: 703467 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.7628. Min Act: -0.0000

Data Index: 815627 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 5.0467. Min Range: -5.0467

Max Act: 2.9905. Min Act: -0.0000

Data Index: 931812 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.4086. Min Act: -0.0000

Data Index: 549614 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.2217. Min Act: -0.0000

Data Index: 1190349 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 5.0467. Min Range: -5.0467

Max Act: 2.9276. Min Act: -0.0000

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 5.0467. Min Range: -5.0467

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1278397 (C4 (Web Text))

Max Activating Token Index: 347