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

Dataset: The Pile

Neuron 2039 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0154. Min Range: -1.0154

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1519907 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 1.0154. Min Range: -1.0154

Max Act: 1.0079. Min Act: -0.0000

Data Index: 652035 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1674767 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1227255 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8282. Min Act: -0.0000

Data Index: 470692 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8251. Min Act: -0.0000

Data Index: 193222 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7887. Min Act: -0.0000

Data Index: 406839 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8304. Min Act: -0.0000

Data Index: 553857 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8143. Min Act: -0.0000

Data Index: 465926 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8597. Min Act: -0.0000

Data Index: 890837 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7952. Min Act: -0.0000

Data Index: 627857 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7708. Min Act: -0.0000

Data Index: 914846 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7932. Min Act: -0.0000

Data Index: 910693 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1354976 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1559500 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1063817 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1685383 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1538636 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1226125 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6696. Min Act: -0.0000

Data Index: 697363 (The Pile)

Max Activating Token Index: 456