Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1704261 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1565994 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1670712 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3236. Min Act: -0.0000

Data Index: 587294 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3310. Min Act: -0.0000

Data Index: 766243 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1540455 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3122. Min Act: -0.0000

Data Index: 16998 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1187504 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1439565 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3113. Min Act: -0.0000

Data Index: 994406 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3003. Min Act: -0.0000

Data Index: 345668 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3516. Min Act: -0.0000

Data Index: 127690 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3169. Min Act: -0.0000

Data Index: 184060 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2975. Min Act: -0.0000

Data Index: 794139 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1973184 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2732. Min Act: -0.0000

Data Index: 842375 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1225505 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2596. Min Act: -0.0000

Data Index: 656277 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2670. Min Act: -0.0000

Data Index: 536066 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1122864 (The Pile)

Max Activating Token Index: 542