Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1132 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1177895 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1163816 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.3021. Min Act: -0.0000

Data Index: 834541 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.4236. Min Act: -0.0000

Data Index: 818164 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2423. Min Act: -0.0000

Data Index: 581275 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1008751 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.1113. Min Act: -0.0000

Data Index: 974505 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0943. Min Act: -0.0000

Data Index: 679526 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0955. Min Act: 0.0000

Data Index: 1116876 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.2148. Min Act: -0.0000

Data Index: 813996 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0654. Min Act: -0.0000

Data Index: 973996 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1669445 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1738186 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0363. Min Act: -0.0000

Data Index: 303412 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.5604. Min Range: -1.5604

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1541704 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 1.5604. Min Range: -1.5604

Max Act: 0.8543. Min Act: -0.0000

Data Index: 36335 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 1.5604. Min Range: -1.5604

Max Act: 0.9754. Min Act: 0.0000

Data Index: 178412 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0627. Min Act: -0.0000

Data Index: 870725 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.5604. Min Range: -1.5604

Max Act: 1.0334. Min Act: 0.0000

Data Index: 175736 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 1.5604. Min Range: -1.5604

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1864569 (The Pile)

Max Activating Token Index: 322