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

Dataset: The Pile

Neuron 4824 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: 3.7154. Min Range: -3.7154

Max Act: 3.7154. Min Act: -0.0000

Data Index: 837712 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.2187. Min Act: -0.0000

Data Index: 1664849 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.3893. Min Act: -0.0000

Data Index: 88925 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.0393. Min Act: -0.0000

Data Index: 771409 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.1992. Min Act: -0.0000

Data Index: 126237 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.1952. Min Act: -0.0000

Data Index: 681555 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.9474. Min Act: -0.0000

Data Index: 978073 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.2606. Min Act: -0.0000

Data Index: 845184 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.9141. Min Act: -0.0000

Data Index: 1586313 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.0580. Min Act: -0.0000

Data Index: 180372 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.9283. Min Act: -0.0000

Data Index: 1545612 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.6588. Min Act: -0.0000

Data Index: 1135534 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.9234. Min Act: -0.0000

Data Index: 526187 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1905565 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.8714. Min Act: -0.0000

Data Index: 482154 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.8415. Min Act: -0.0000

Data Index: 1263869 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.0979. Min Act: -0.0000

Data Index: 1644867 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.7683. Min Act: -0.0000

Data Index: 15119 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.6801. Min Act: -0.0000

Data Index: 969379 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 3.7154. Min Range: -3.7154

Max Act: 2.5803. Min Act: -0.0000

Data Index: 238987 (The Pile)

Max Activating Token Index: 579