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

Dataset: The Pile

Neuron 1877 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: 0.9238. Min Range: -0.9238

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1024758 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8428. Min Act: -0.0000

Data Index: 3292 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.8678. Min Act: -0.0000

Data Index: 788227 (The Pile)

Max Activating Token Index: 752

Text #3

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1970028 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7628. Min Act: -0.0000

Data Index: 135676 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1881436 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1234708 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6619. Min Act: -0.0000

Data Index: 984748 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1644325 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1834278 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6421. Min Act: -0.0000

Data Index: 611129 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1225331 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6732. Min Act: -0.0000

Data Index: 669049 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6480. Min Act: -0.0000

Data Index: 993936 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5927. Min Act: -0.0000

Data Index: 669335 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1702700 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6431. Min Act: -0.0000

Data Index: 865639 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.6091. Min Act: -0.0000

Data Index: 286448 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1152058 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1622996 (The Pile)

Max Activating Token Index: 239