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

Dataset: The Pile

Neuron 733 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: 7.7439. Min Range: -7.7439

Max Act: 7.7439. Min Act: -0.0000

Data Index: 1688433 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 7.7439. Min Range: -7.7439

Max Act: 7.0193. Min Act: -0.0000

Data Index: 1831628 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.8108. Min Act: -0.0000

Data Index: 1339884 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.1414. Min Act: -0.0000

Data Index: 1251032 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.9092. Min Act: -0.0000

Data Index: 1554841 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.3727. Min Act: -0.0000

Data Index: 823418 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.8265. Min Act: -0.0000

Data Index: 1871340 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.7101. Min Act: -0.0000

Data Index: 1507238 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.1897. Min Act: -0.0000

Data Index: 1538045 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.0085. Min Act: -0.0000

Data Index: 98754 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.0921. Min Act: -0.0000

Data Index: 97556 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.0443. Min Act: -0.0000

Data Index: 1141139 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 7.7439. Min Range: -7.7439

Max Act: 6.0630. Min Act: -0.0000

Data Index: 1723205 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.6638. Min Act: -0.0000

Data Index: 744666 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.8163. Min Act: -0.0000

Data Index: 1290859 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.4338. Min Act: -0.0000

Data Index: 924613 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.8303. Min Act: -0.0000

Data Index: 334267 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.3037. Min Act: -0.0000

Data Index: 1582656 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.0947. Min Act: -0.0000

Data Index: 921336 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 7.7439. Min Range: -7.7439

Max Act: 5.7997. Min Act: -0.0000

Data Index: 1069426 (The Pile)

Max Activating Token Index: 605