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

Dataset: The Pile

Neuron 38 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.8593. Min Act: -0.0000

Data Index: 628163 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1595343 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1295901 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5573. Min Act: -0.0000

Data Index: 525083 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1034506 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1635267 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4665. Min Act: -0.0000

Data Index: 737876 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4462. Min Act: -0.0000

Data Index: 139082 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1173365 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4307. Min Act: -0.0000

Data Index: 775600 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4120. Min Act: -0.0000

Data Index: 98606 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2806. Min Act: -0.0000

Data Index: 449206 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3182. Min Act: -0.0000

Data Index: 173900 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1522960 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3331. Min Act: -0.0000

Data Index: 81409 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1272105 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1997129 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3167. Min Act: -0.0000

Data Index: 953619 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2602. Min Act: -0.0000

Data Index: 449157 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1465411 (The Pile)

Max Activating Token Index: 508