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

Dataset: The Pile

Neuron 1985 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.2328. Min Act: -0.0000

Data Index: 767152 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.1371. Min Act: -0.0000

Data Index: 426904 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0585. Min Act: 0.0000

Data Index: 1088006 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 1.2328. Min Range: -1.2328

Max Act: 1.0436. Min Act: -0.0000

Data Index: 696880 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1040169 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1521819 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1412296 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8972. Min Act: 0.0000

Data Index: 447991 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9519. Min Act: 0.0000

Data Index: 200714 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9261. Min Act: -0.0000

Data Index: 739218 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8944. Min Act: -0.0000

Data Index: 939672 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8984. Min Act: -0.0000

Data Index: 193270 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1498353 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8677. Min Act: -0.0000

Data Index: 795772 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8724. Min Act: -0.0000

Data Index: 963891 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8666. Min Act: 0.0000

Data Index: 1971892 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1669208 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1522278 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1121011 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 1.2328. Min Range: -1.2328

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1592540 (The Pile)

Max Activating Token Index: 954