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

Dataset: The Pile

Neuron 3016 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6817. Min Act: -0.0000

Data Index: 1423162 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3913. Min Act: -0.0000

Data Index: 602372 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1695897 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1296584 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1960279 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1610. Min Act: -0.0000

Data Index: 679428 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1556762 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1396. Min Act: -0.0000

Data Index: 200886 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1988. Min Act: -0.0000

Data Index: 865580 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1359856 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3624. Min Act: -0.0000

Data Index: 809875 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1769. Min Act: -0.0000

Data Index: 102265 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1525429 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1870. Min Act: -0.0000

Data Index: 340234 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1938. Min Act: -0.0000

Data Index: 215311 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1302. Min Act: -0.0000

Data Index: 28030 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1814978 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1380100 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.0684. Min Act: -0.0000

Data Index: 506731 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.0236. Min Act: -0.0000

Data Index: 910792 (The Pile)

Max Activating Token Index: 43