Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.3530. Min Act: -0.0000

Data Index: 1616790 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.7842. Min Act: -0.0000

Data Index: 1756321 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.1068. Min Act: -0.0000

Data Index: 674112 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1431192 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.5888. Min Act: -0.0000

Data Index: 939946 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.6190. Min Act: -0.0000

Data Index: 39706 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.5714. Min Act: -0.0000

Data Index: 85612 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.6538. Min Act: -0.0000

Data Index: 1401589 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.5198. Min Act: -0.0000

Data Index: 1186377 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.4533. Min Act: -0.0000

Data Index: 1424024 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.3415. Min Act: -0.0000

Data Index: 1593920 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.3209. Min Act: -0.0000

Data Index: 843694 (The Pile)

Max Activating Token Index: 518

Text #12

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.3181. Min Act: -0.0000

Data Index: 688187 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.3126. Min Act: -0.0000

Data Index: 1827070 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.4198. Min Act: -0.0000

Data Index: 1436167 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.4077. Min Act: -0.0000

Data Index: 1574495 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.5311. Min Act: -0.0000

Data Index: 708634 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.2314. Min Act: -0.0000

Data Index: 1250900 (The Pile)

Max Activating Token Index: 764

Text #18

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.4567. Min Act: -0.0000

Data Index: 573445 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.4475. Min Act: -0.0000

Data Index: 1422768 (The Pile)

Max Activating Token Index: 25