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

Dataset: The Pile

Neuron 1768 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: 1.8528. Min Range: -1.8528

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1235174 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.6841. Min Act: -0.0000

Data Index: 998441 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1752946 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5469. Min Act: -0.0000

Data Index: 159884 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5368. Min Act: -0.0000

Data Index: 959311 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5334. Min Act: -0.0000

Data Index: 867201 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1128971 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4804. Min Act: -0.0000

Data Index: 335045 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1214873 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5494. Min Act: -0.0000

Data Index: 693588 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4669. Min Act: -0.0000

Data Index: 415324 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4413. Min Act: -0.0000

Data Index: 80107 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5232. Min Act: -0.0000

Data Index: 432954 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.3586. Min Act: -0.0000

Data Index: 827879 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4135. Min Act: -0.0000

Data Index: 325577 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4091. Min Act: -0.0000

Data Index: 664740 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1471925 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.3773. Min Act: -0.0000

Data Index: 653735 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4714. Min Act: -0.0000

Data Index: 100129 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 1.8528. Min Range: -1.8528

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1138158 (The Pile)

Max Activating Token Index: 53