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

Dataset: The Pile

Neuron 3951 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: 0.9964. Min Range: -0.9964

Max Act: 0.9964. Min Act: -0.0000

Data Index: 279363 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1566054 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8554. Min Act: -0.0000

Data Index: 650789 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9003. Min Act: -0.0000

Data Index: 884913 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7984. Min Act: -0.0000

Data Index: 3472 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7217. Min Act: -0.0000

Data Index: 948247 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7028. Min Act: 0.0000

Data Index: 1173394 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1776942 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1109948 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7392. Min Act: -0.0000

Data Index: 345714 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1886573 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6430. Min Act: 0.0000

Data Index: 24332 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6513. Min Act: -0.0000

Data Index: 480603 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6877. Min Act: 0.0000

Data Index: 777988 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1184434 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1910696 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6561. Min Act: -0.0000

Data Index: 540069 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1947244 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1485937 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6391. Min Act: -0.0000

Data Index: 458150 (The Pile)

Max Activating Token Index: 444