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

Dataset: The Pile

Neuron 1952 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: 0.9807. Min Range: -0.9807

Max Act: 0.9465. Min Act: 0.0000

Data Index: 1081643 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9807. Min Act: 0.0000

Data Index: 399631 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9320. Min Act: -0.0000

Data Index: 382670 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9281. Min Act: 0.0000

Data Index: 549364 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8777. Min Act: -0.0000

Data Index: 859146 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8504. Min Act: 0.0000

Data Index: 1592410 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1635474 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1488911 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8708. Min Act: 0.0000

Data Index: 711279 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9268. Min Act: 0.0001

Data Index: 1786499 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8635. Min Act: -0.0000

Data Index: 612717 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1565209 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1768701 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8473. Min Act: -0.0000

Data Index: 115976 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1947904 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1371792 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1743132 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8037. Min Act: -0.0000

Data Index: 442364 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7989. Min Act: 0.0000

Data Index: 806900 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8256. Min Act: 0.0001

Data Index: 1435083 (The Pile)

Max Activating Token Index: 574