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

Dataset: The Pile

Neuron 1364 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: 0.5789. Min Range: -0.5789

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1427571 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1027398 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1909666 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5584. Min Act: -0.0000

Data Index: 873581 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5117. Min Act: -0.0000

Data Index: 768680 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5218. Min Act: 0.0000

Data Index: 912352 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1594602 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5179. Min Act: -0.0000

Data Index: 763027 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4958. Min Act: 0.0000

Data Index: 1365707 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4998. Min Act: 0.0000

Data Index: 997600 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1179819 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1621490 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4739. Min Act: -0.0000

Data Index: 76109 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4914. Min Act: -0.0000

Data Index: 124183 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4675. Min Act: -0.0000

Data Index: 14779 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1133598 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1269520 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1193626 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1959262 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1808156 (The Pile)

Max Activating Token Index: 549