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

Dataset: The Pile

Neuron 867 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: 1.1553. Min Range: -1.1553

Max Act: 1.1553. Min Act: -0.0000

Data Index: 654909 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 1.1553. Min Range: -1.1553

Max Act: 1.0075. Min Act: 0.0000

Data Index: 1984956 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.7913. Min Act: 0.0000

Data Index: 1460291 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.8137. Min Act: -0.0000

Data Index: 183163 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.8592. Min Act: -0.0000

Data Index: 371166 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1704704 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.7127. Min Act: -0.0000

Data Index: 155725 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.6542. Min Act: 0.0000

Data Index: 576076 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.6592. Min Act: -0.0000

Data Index: 816879 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1214803 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5141. Min Act: -0.0000

Data Index: 470069 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1457310 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.6548. Min Act: -0.0000

Data Index: 379382 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5543. Min Act: 0.0000

Data Index: 502540 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5955. Min Act: -0.0000

Data Index: 338384 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5537. Min Act: 0.0000

Data Index: 1111974 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1860688 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5685. Min Act: 0.0000

Data Index: 289625 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1465673 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 1.1553. Min Range: -1.1553

Max Act: 0.5244. Min Act: -0.0000

Data Index: 130029 (The Pile)

Max Activating Token Index: 462