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

Dataset: The Pile

Neuron 1191 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.5582. Min Act: -0.0000

Data Index: 699992 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.1518. Min Act: -0.0000

Data Index: 14942 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 3.5582. Min Range: -3.5582

Max Act: 3.0866. Min Act: -0.0000

Data Index: 1530052 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.9960. Min Act: -0.0000

Data Index: 1152682 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.8134. Min Act: -0.0000

Data Index: 895521 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.7613. Min Act: -0.0000

Data Index: 307390 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.5421. Min Act: -0.0000

Data Index: 757823 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.6364. Min Act: -0.0000

Data Index: 218255 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.6534. Min Act: -0.0000

Data Index: 1702021 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.3021. Min Act: -0.0000

Data Index: 999595 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.2582. Min Act: -0.0000

Data Index: 628131 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1436760 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1805176 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 3.5582. Min Range: -3.5582

Max Act: 2.0535. Min Act: -0.0000

Data Index: 1027398 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.8142. Min Act: -0.0000

Data Index: 145053 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.7637. Min Act: -0.0000

Data Index: 809790 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1187298 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.7061. Min Act: -0.0000

Data Index: 954194 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.7109. Min Act: -0.0000

Data Index: 461263 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 3.5582. Min Range: -3.5582

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1719045 (The Pile)

Max Activating Token Index: 522