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

Dataset: The Pile

Neuron 3679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1466801 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9594. Min Act: -0.0000

Data Index: 999479 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1363107 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9747. Min Act: -0.0000

Data Index: 170210 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0419. Min Act: -0.0000

Data Index: 870175 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1107585 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1617571 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1919340 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1607298 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9040. Min Act: -0.0000

Data Index: 801346 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0170. Min Act: -0.0000

Data Index: 215553 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1449438 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1018566 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.7627. Min Act: -0.0000

Data Index: 576463 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1302525 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.7930. Min Act: -0.0000

Data Index: 361593 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9520. Min Act: -0.0000

Data Index: 849524 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1050254 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8984. Min Act: -0.0000

Data Index: 710909 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1581766 (The Pile)

Max Activating Token Index: 536