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

Dataset: The Pile

Neuron 138 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: 1.6474. Min Range: -1.6474

Max Act: 1.6474. Min Act: -0.0000

Data Index: 959828 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1585636 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.4897. Min Act: -0.0000

Data Index: 1182457 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5247. Min Act: -0.0000

Data Index: 117473 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.4563. Min Act: -0.0000

Data Index: 565290 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1796995 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3470. Min Act: -0.0000

Data Index: 1675505 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3911. Min Act: -0.0000

Data Index: 92544 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1952579 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1119554 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3342. Min Act: -0.0000

Data Index: 400456 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1518369 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.2670. Min Act: -0.0000

Data Index: 426240 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3265. Min Act: -0.0000

Data Index: 541310 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.2067. Min Act: -0.0000

Data Index: 815005 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1014940 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1566576 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1423567 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1792957 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1394145 (The Pile)

Max Activating Token Index: 273