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

Dataset: The Pile

Neuron 3263 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: 0.6296. Min Range: -0.6296

Max Act: 0.5778. Min Act: -0.0000

Data Index: 857669 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.6296. Min Act: -0.0000

Data Index: 179000 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.6287. Min Act: -0.0000

Data Index: 629502 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5288. Min Act: -0.0000

Data Index: 359253 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1805362 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1325067 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1572616 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5573. Min Act: -0.0000

Data Index: 324860 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5674. Min Act: -0.0000

Data Index: 900698 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1784047 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4744. Min Act: -0.0000

Data Index: 108175 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1041962 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5783. Min Act: -0.0000

Data Index: 552921 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4958. Min Act: -0.0000

Data Index: 732024 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1116652 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5261. Min Act: -0.0000

Data Index: 698649 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5561. Min Act: -0.0000

Data Index: 678765 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1037610 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1885945 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4849. Min Act: -0.0000

Data Index: 564132 (The Pile)

Max Activating Token Index: 180