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

Dataset: The Pile

Neuron 4870 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: 0.8203. Min Range: -0.8203

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1949226 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1593837 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1348525 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1688536 (The Pile)

Max Activating Token Index: 566

Text #4

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5963. Min Act: -0.0000

Data Index: 37062 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1108707 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5900. Min Act: -0.0000

Data Index: 978821 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1615628 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1993130 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1495096 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1014673 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1283906 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5318. Min Act: -0.0000

Data Index: 122806 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5706. Min Act: -0.0000

Data Index: 474983 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1043021 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1473775 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1350769 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5120. Min Act: -0.0000

Data Index: 436053 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5054. Min Act: -0.0000

Data Index: 6375 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1153173 (The Pile)

Max Activating Token Index: 174