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

Dataset: The Pile

Neuron 2016 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1849304 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8123. Min Act: -0.0000

Data Index: 991428 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7885. Min Act: -0.0001

Data Index: 1250106 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1328809 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7988. Min Act: -0.0000

Data Index: 696797 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7445. Min Act: -0.0000

Data Index: 410178 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1249678 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7204. Min Act: -0.0000

Data Index: 958381 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1355592 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1363926 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7428. Min Act: -0.0000

Data Index: 427779 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1394107 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7237. Min Act: -0.0000

Data Index: 849580 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1760507 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1976242 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7896. Min Act: -0.0000

Data Index: 188068 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7343. Min Act: -0.0001

Data Index: 60544 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1303778 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7322. Min Act: -0.0000

Data Index: 65454 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1184715 (The Pile)

Max Activating Token Index: 286