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

Dataset: The Pile

Neuron 1991 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: 1.2407. Min Range: -1.2407

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1295898 (The Pile)

Max Activating Token Index: 422

Text #1

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1936201 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1778219 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.1117. Min Act: -0.0000

Data Index: 514402 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1196304 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.0851. Min Act: -0.0000

Data Index: 139065 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.2407. Min Range: -1.2407

Max Act: 1.0357. Min Act: -0.0000

Data Index: 647041 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1118385 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1017618 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1891195 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9464. Min Act: -0.0000

Data Index: 620503 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1072629 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1189438 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8674. Min Act: -0.0000

Data Index: 688839 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.9151. Min Act: -0.0000

Data Index: 69717 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8324. Min Act: -0.0000

Data Index: 475228 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1119750 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1547588 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.7491. Min Act: -0.0000

Data Index: 475463 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 1.2407. Min Range: -1.2407

Max Act: 0.8269. Min Act: -0.0000

Data Index: 134038 (The Pile)

Max Activating Token Index: 392