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

Dataset: The Pile

Neuron 2992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.3152. Min Act: -0.0000

Data Index: 174043 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.1271. Min Act: -0.0000

Data Index: 894103 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1944273 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9838. Min Act: -0.0000

Data Index: 887106 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1373178 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.1706. Min Act: -0.0000

Data Index: 266266 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1950858 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1072876 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0790. Min Act: -0.0000

Data Index: 175444 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1073969 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1364442 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9306. Min Act: -0.0000

Data Index: 617772 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1197050 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9674. Min Act: -0.0000

Data Index: 729549 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0034. Min Act: -0.0000

Data Index: 837657 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0146. Min Act: -0.0000

Data Index: 746262 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1434065 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9637. Min Act: -0.0000

Data Index: 903999 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9977. Min Act: -0.0000

Data Index: 508665 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9292. Min Act: -0.0000

Data Index: 398210 (The Pile)

Max Activating Token Index: 554