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

Dataset: The Pile

Neuron 1156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1342440 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4283. Min Act: -0.0000

Data Index: 572780 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1321925 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3829. Min Act: -0.0000

Data Index: 95937 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3676. Min Act: -0.0000

Data Index: 299524 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1658098 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3731. Min Act: -0.0000

Data Index: 514621 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1043895 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3559. Min Act: -0.0000

Data Index: 902224 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1066680 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3337. Min Act: -0.0000

Data Index: 376218 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1425727 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3268. Min Act: -0.0000

Data Index: 799320 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3242. Min Act: -0.0000

Data Index: 838876 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3275. Min Act: -0.0000

Data Index: 236031 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1408291 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1711389 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1240664 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1649436 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1736175 (The Pile)

Max Activating Token Index: 211