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

Dataset: The Pile

Neuron 271 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: 1.6869. Min Range: -1.6869

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1352025 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.5995. Min Act: -0.0000

Data Index: 980140 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6416. Min Act: -0.0000

Data Index: 782138 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6869. Min Act: -0.0000

Data Index: 166802 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1620892 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4575. Min Act: -0.0000

Data Index: 1308392 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4969. Min Act: -0.0000

Data Index: 385454 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2347. Min Act: -0.0000

Data Index: 94378 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1522990 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1290962 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4502. Min Act: -0.0000

Data Index: 328030 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3901. Min Act: -0.0000

Data Index: 444400 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1316339 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1303799 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3049. Min Act: -0.0000

Data Index: 536549 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4051. Min Act: -0.0000

Data Index: 189329 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3850. Min Act: -0.0000

Data Index: 258517 (The Pile)

Max Activating Token Index: 653

Text #17

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1188193 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.1484. Min Act: -0.0000

Data Index: 824648 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2065. Min Act: -0.0000

Data Index: 709413 (The Pile)

Max Activating Token Index: 666