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

Dataset: The Pile

Neuron 3664 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: 0.5247. Min Range: -0.5247

Max Act: 0.5247. Min Act: -0.0000

Data Index: 365291 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4995. Min Act: -0.0000

Data Index: 490894 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1277661 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1911970 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1506937 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4596. Min Act: -0.0000

Data Index: 784025 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1244958 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4629. Min Act: -0.0000

Data Index: 844420 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1192253 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1539530 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1599768 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3816. Min Act: -0.0000

Data Index: 681214 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1808434 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4471. Min Act: -0.0000

Data Index: 444627 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1971844 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4433. Min Act: -0.0000

Data Index: 600046 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4082. Min Act: -0.0000

Data Index: 593163 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1024268 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1992420 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4332. Min Act: -0.0000

Data Index: 435168 (The Pile)

Max Activating Token Index: 415