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

Dataset: The Pile

Neuron 4079 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: 4.4800. Min Range: -4.4800

Max Act: 4.4800. Min Act: -0.0000

Data Index: 997522 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 4.4800. Min Range: -4.4800

Max Act: 4.3503. Min Act: -0.0000

Data Index: 1828616 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 4.4800. Min Range: -4.4800

Max Act: 4.3290. Min Act: -0.0000

Data Index: 838671 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 4.4800. Min Range: -4.4800

Max Act: 4.2000. Min Act: -0.0000

Data Index: 407745 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 4.4800. Min Range: -4.4800

Max Act: 4.1692. Min Act: -0.0000

Data Index: 576257 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 4.4800. Min Range: -4.4800

Max Act: 4.0014. Min Act: -0.0000

Data Index: 876260 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.9157. Min Act: -0.0000

Data Index: 2992 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.9227. Min Act: -0.0000

Data Index: 562936 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8771. Min Act: -0.0000

Data Index: 1274563 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8711. Min Act: -0.0000

Data Index: 1605236 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.7086. Min Act: -0.0000

Data Index: 703207 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8558. Min Act: -0.0000

Data Index: 634011 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8302. Min Act: -0.0000

Data Index: 1154419 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.9986. Min Act: -0.0000

Data Index: 1045072 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.6501. Min Act: -0.0000

Data Index: 605622 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8020. Min Act: -0.0000

Data Index: 1721643 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.6183. Min Act: -0.0000

Data Index: 1084158 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.7222. Min Act: -0.0000

Data Index: 1208265 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.6783. Min Act: -0.0000

Data Index: 778860 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 4.4800. Min Range: -4.4800

Max Act: 3.8384. Min Act: -0.0000

Data Index: 1271512 (The Pile)

Max Activating Token Index: 734