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

Dataset: The Pile

Neuron 1134 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.5772. Min Act: -0.0000

Data Index: 606304 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1401541 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1411384 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3611. Min Act: -0.0000

Data Index: 1534205 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.4423. Min Act: -0.0000

Data Index: 532462 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1895160 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1448203 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3669. Min Act: -0.0000

Data Index: 900367 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1660145 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3786. Min Act: -0.0000

Data Index: 332335 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3320. Min Act: -0.0000

Data Index: 140286 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1399357 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3531. Min Act: -0.0000

Data Index: 176467 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1885528 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.4100. Min Act: -0.0000

Data Index: 1466163 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1981463 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1862729 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1140031 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.4154. Min Act: -0.0000

Data Index: 318293 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.6144. Min Range: -1.6144

Max Act: 1.3153. Min Act: -0.0000

Data Index: 571996 (The Pile)

Max Activating Token Index: 957