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

Dataset: The Pile

Neuron 3027 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: 1.7391. Min Range: -1.7391

Max Act: 1.7391. Min Act: -0.0000

Data Index: 947443 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1801455 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1042524 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.3210. Min Act: -0.0000

Data Index: 573143 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1142083 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1225737 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1654849 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1081990 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1879. Min Act: 0.0001

Data Index: 1710503 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1889061 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1488722 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1610. Min Act: -0.0000

Data Index: 23724 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.0368. Min Act: -0.0000

Data Index: 642639 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.0421. Min Act: -0.0000

Data Index: 21306 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1554758 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1923. Min Act: -0.0000

Data Index: 949175 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1694442 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1198. Min Act: -0.0000

Data Index: 667420 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1427. Min Act: -0.0000

Data Index: 837712 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.7391. Min Range: -1.7391

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1298234 (The Pile)

Max Activating Token Index: 680