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

Dataset: The Pile

Neuron 265 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: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 215810 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1297278 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5008. Min Act: -0.0000

Data Index: 566516 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1880355 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1236144 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4861. Min Act: -0.0000

Data Index: 271803 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1809053 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1740483 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4703. Min Act: -0.0000

Data Index: 166349 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4667. Min Act: -0.0000

Data Index: 46321 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4263. Min Act: -0.0000

Data Index: 624081 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1753286 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4384. Min Act: -0.0000

Data Index: 509997 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4562. Min Act: -0.0000

Data Index: 201690 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4331. Min Act: -0.0000

Data Index: 487433 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1829191 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1534996 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1353325 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4282. Min Act: -0.0000

Data Index: 537601 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1387942 (The Pile)

Max Activating Token Index: 1019