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

Dataset: The Pile

Neuron 2870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.6076. Min Act: -0.0000

Data Index: 697411 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1059354 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1820876 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5351. Min Act: -0.0000

Data Index: 593373 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1290844 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1290520 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1705656 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1826695 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4688. Min Act: -0.0000

Data Index: 360445 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1151434 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1459992 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1238255 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1552402 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4337. Min Act: -0.0000

Data Index: 948925 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1465684 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1492816 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4131. Min Act: -0.0000

Data Index: 268851 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4091. Min Act: -0.0000

Data Index: 439907 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4165. Min Act: -0.0000

Data Index: 738268 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1790662 (The Pile)

Max Activating Token Index: 280