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

Dataset: The Pile

Neuron 4712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1263. Min Range: -5.1263

Max Act: 5.1263. Min Act: -0.0000

Data Index: 1666418 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.3828. Min Act: -0.0000

Data Index: 39570 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.8442. Min Act: -0.0000

Data Index: 746207 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.5645. Min Act: -0.0000

Data Index: 1354250 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.7270. Min Act: -0.0000

Data Index: 511303 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.7889. Min Act: -0.0000

Data Index: 64777 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.3654. Min Act: -0.0000

Data Index: 947163 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.4469. Min Act: -0.0000

Data Index: 1933907 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.2479. Min Act: -0.0000

Data Index: 661740 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.5008. Min Act: -0.0000

Data Index: 495878 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.2491. Min Act: -0.0000

Data Index: 1714896 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.1164. Min Act: -0.0000

Data Index: 424289 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.2548. Min Act: -0.0000

Data Index: 979084 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.0935. Min Act: -0.0000

Data Index: 1879856 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.1803. Min Act: -0.0000

Data Index: 1310817 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.0225. Min Act: -0.0000

Data Index: 1937749 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 5.1263. Min Range: -5.1263

Max Act: 2.8411. Min Act: -0.0000

Data Index: 440699 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 5.1263. Min Range: -5.1263

Max Act: 2.8142. Min Act: -0.0000

Data Index: 406076 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 5.1263. Min Range: -5.1263

Max Act: 2.8090. Min Act: -0.0000

Data Index: 182197 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 5.1263. Min Range: -5.1263

Max Act: 3.1507. Min Act: -0.0000

Data Index: 345313 (The Pile)

Max Activating Token Index: 857