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

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

Neuron 508 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3904. Min Act: -0.0001

Data Index: 433343 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3704. Min Act: -0.0001

Data Index: 24916 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3360. Min Act: -0.0001

Data Index: 531953 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3442. Min Act: -0.0001

Data Index: 52882 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3434. Min Act: -0.0001

Data Index: 253245 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2974. Min Act: -0.0001

Data Index: 772253 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2866. Min Act: -0.0001

Data Index: 753293 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1336013 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2765. Min Act: -0.0001

Data Index: 606358 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2860. Min Act: -0.0001

Data Index: 349165 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2614. Min Act: -0.0001

Data Index: 622192 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2777. Min Act: -0.0001

Data Index: 606760 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2742. Min Act: -0.0001

Data Index: 826967 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2569. Min Act: -0.0001

Data Index: 889660 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2583. Min Act: -0.0001

Data Index: 57183 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2463. Min Act: -0.0001

Data Index: 155219 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2454. Min Act: -0.0001

Data Index: 213839 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2287. Min Act: -0.0001

Data Index: 196931 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2400. Min Act: -0.0001

Data Index: 25874 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2382. Min Act: -0.0001

Data Index: 764114 (C4 (Web Text))

Max Activating Token Index: 565