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

Dataset: The Pile

Neuron 5109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1058325 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1182890 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1304274 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1825690 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1316015 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1135480 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1559. Min Act: -0.0000

Data Index: 519922 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1666645 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1411. Min Act: -0.0000

Data Index: 744846 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1605517 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1018430 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1365. Min Act: -0.0000

Data Index: 794918 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1158175 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1833951 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1023033 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1648869 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.0811. Min Act: -0.0000

Data Index: 114934 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.1517. Min Act: -0.0000

Data Index: 4921 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.0720. Min Act: -0.0000

Data Index: 789449 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.3162. Min Range: -1.3162

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1131550 (The Pile)

Max Activating Token Index: 846