Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3272 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1513276 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1334350 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7148. Min Act: -0.0000

Data Index: 951856 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7417. Min Act: -0.0000

Data Index: 210118 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1024957 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6934. Min Act: -0.0000

Data Index: 471513 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1583336 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6857. Min Act: -0.0000

Data Index: 985202 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6888. Min Act: -0.0000

Data Index: 268262 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6827. Min Act: -0.0000

Data Index: 2229 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1811281 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6606. Min Act: -0.0000

Data Index: 538090 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6383. Min Act: -0.0000

Data Index: 510208 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6763. Min Act: -0.0000

Data Index: 58236 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1277379 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6401. Min Act: -0.0000

Data Index: 118117 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6674. Min Act: -0.0000

Data Index: 967161 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1911288 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6203. Min Act: -0.0000

Data Index: 76664 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1650076 (The Pile)

Max Activating Token Index: 530