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

Dataset: The Pile

Neuron 3271 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0001

Data Index: 511067 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4759. Min Act: -0.0000

Data Index: 39191 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4514. Min Act: -0.0000

Data Index: 229671 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1348328 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4390. Min Act: -0.0000

Data Index: 503190 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1296649 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4160. Min Act: -0.0000

Data Index: 511100 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1018987 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1471338 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1695974 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1079647 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1926628 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1808562 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3892. Min Act: -0.0000

Data Index: 605523 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3764. Min Act: -0.0000

Data Index: 763605 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3706. Min Act: -0.0000

Data Index: 291133 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1696201 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3419. Min Act: -0.0000

Data Index: 462089 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1938854 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1789370 (The Pile)

Max Activating Token Index: 294