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

Dataset: The Pile

Neuron 3157 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: 1.4220. Min Range: -1.4220

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1553319 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1971. Min Act: -0.0000

Data Index: 63287 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1161119 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1676775 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1505. Min Act: -0.0000

Data Index: 444099 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1133. Min Act: -0.0000

Data Index: 350888 (The Pile)

Max Activating Token Index: 3

Text #6

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1745736 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.1177. Min Act: -0.0000

Data Index: 88426 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0249. Min Act: -0.0000

Data Index: 812579 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1201967 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1914319 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1640236 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1961070 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 1.4220. Min Range: -1.4220

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1364655 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8920. Min Act: -0.0000

Data Index: 866275 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9084. Min Act: -0.0000

Data Index: 588393 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9629. Min Act: -0.0000

Data Index: 43293 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.9883. Min Act: -0.0000

Data Index: 24277 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8976. Min Act: -0.0000

Data Index: 511282 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 1.4220. Min Range: -1.4220

Max Act: 0.8990. Min Act: -0.0000

Data Index: 409827 (The Pile)

Max Activating Token Index: 905