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

Dataset: The Pile

Neuron 3796 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4734. Min Act: -0.0000

Data Index: 1703668 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1172057 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.4378. Min Act: -0.0000

Data Index: 584687 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3574. Min Act: -0.0000

Data Index: 407248 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2588. Min Act: -0.0000

Data Index: 445761 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1577886 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.3758. Min Act: -0.0000

Data Index: 95900 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2779. Min Act: -0.0000

Data Index: 631928 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2033. Min Act: -0.0000

Data Index: 831691 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1054321 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2526. Min Act: -0.0000

Data Index: 844050 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2082. Min Act: -0.0000

Data Index: 202650 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2300. Min Act: -0.0000

Data Index: 303179 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2630. Min Act: -0.0000

Data Index: 272427 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1644074 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1672392 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1161335 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1554. Min Act: -0.0000

Data Index: 266570 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1751630 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 1.4755. Min Range: -1.4755

Max Act: 1.2178. Min Act: -0.0000

Data Index: 455089 (The Pile)

Max Activating Token Index: 446