Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1004789 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0003

Data Index: 869257 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1050217 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0292. Min Act: -0.0003

Data Index: 762354 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0305. Min Act: -0.0003

Data Index: 615737 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0278. Min Act: -0.0003

Data Index: 236300 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0285. Min Act: -0.0003

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1306413 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0288. Min Act: -0.0003

Data Index: 962474 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0266. Min Act: -0.0003

Data Index: 37430 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1018003 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0278. Min Act: -0.0003

Data Index: 396880 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1281888 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0267. Min Act: -0.0003

Data Index: 491858 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0283. Min Act: -0.0003

Data Index: 715015 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0262. Min Act: -0.0003

Data Index: 349802 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0273. Min Act: -0.0003

Data Index: 613686 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0266. Min Act: -0.0003

Data Index: 396024 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0255. Min Act: -0.0003

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0249. Min Act: -0.0003

Data Index: 656742 (C4 (Web Text))

Max Activating Token Index: 271