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

Dataset: The Pile

Neuron 1275 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: 1.6523. Min Range: -1.6523

Max Act: 1.6523. Min Act: -0.0000

Data Index: 834362 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1256322 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3281. Min Act: -0.0000

Data Index: 557256 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1262. Min Act: -0.0000

Data Index: 181390 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1242577 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.2447. Min Act: -0.0000

Data Index: 487714 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1356253 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.2478. Min Act: -0.0000

Data Index: 705617 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1550. Min Act: -0.0000

Data Index: 908728 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1699016 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0846. Min Act: -0.0000

Data Index: 230153 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0479. Min Act: -0.0000

Data Index: 428667 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1790652 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.1428. Min Act: -0.0000

Data Index: 992587 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9638. Min Act: -0.0000

Data Index: 588906 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9344. Min Act: -0.0000

Data Index: 226676 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1289069 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1112917 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.9399. Min Act: -0.0000

Data Index: 884966 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 1.6523. Min Range: -1.6523

Max Act: 0.8377. Min Act: -0.0000

Data Index: 491701 (The Pile)

Max Activating Token Index: 158