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

Dataset: The Pile

Neuron 2590 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: 1.0763. Min Range: -1.0763

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1643349 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0380. Min Act: -0.0000

Data Index: 612988 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1463197 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0312. Min Act: -0.0000

Data Index: 709385 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9757. Min Act: -0.0000

Data Index: 901079 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9644. Min Act: -0.0000

Data Index: 515839 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1305771 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1143230 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0107. Min Act: -0.0000

Data Index: 997408 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1675092 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9464. Min Act: 0.0000

Data Index: 1187552 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 1.0763. Min Range: -1.0763

Max Act: 1.0290. Min Act: -0.0000

Data Index: 655008 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1137612 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9076. Min Act: -0.0000

Data Index: 415688 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9668. Min Act: -0.0000

Data Index: 923868 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9946. Min Act: -0.0000

Data Index: 249500 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9018. Min Act: -0.0000

Data Index: 250317 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9127. Min Act: -0.0000

Data Index: 223567 (The Pile)

Max Activating Token Index: 952

Text #18

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9124. Min Act: -0.0000

Data Index: 117827 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.9315. Min Act: 0.0000

Data Index: 1067725 (The Pile)

Max Activating Token Index: 619