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

Dataset: The Pile

Neuron 1213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8438. Min Act: -0.0000

Data Index: 213486 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1793318 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1554667 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1136045 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6930. Min Act: -0.0000

Data Index: 278238 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7146. Min Act: -0.0000

Data Index: 728926 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1314579 (The Pile)

Max Activating Token Index: 629

Text #7

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1836805 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1504348 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1246925 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1914037 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5958. Min Act: -0.0000

Data Index: 144711 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1152890 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5605. Min Act: -0.0000

Data Index: 349692 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6002. Min Act: -0.0000

Data Index: 550106 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1480167 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1083454 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1748581 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1541113 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1334312 (The Pile)

Max Activating Token Index: 365