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

Dataset: The Pile

Neuron 1929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.3233. Min Act: -0.0000

Data Index: 1094737 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1579. Min Act: -0.0000

Data Index: 1476612 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1492. Min Act: -0.0000

Data Index: 160550 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1486. Min Act: -0.0000

Data Index: 1137421 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.7966. Min Act: -0.0000

Data Index: 1701751 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.7672. Min Act: -0.0000

Data Index: 1604238 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.9729. Min Act: -0.0000

Data Index: 1825376 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.5568. Min Act: -0.0000

Data Index: 1491677 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.7104. Min Act: -0.0000

Data Index: 1602097 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.7141. Min Act: -0.0000

Data Index: 1020705 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.6466. Min Act: -0.0000

Data Index: 1916469 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.3025. Min Act: -0.0000

Data Index: 1997033 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.4655. Min Act: -0.0000

Data Index: 964420 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.4637. Min Act: -0.0000

Data Index: 514349 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.6191. Min Act: -0.0000

Data Index: 952399 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.4632. Min Act: -0.0000

Data Index: 1040481 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.4416. Min Act: -0.0000

Data Index: 1190250 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.3882. Min Act: -0.0000

Data Index: 845513 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.3751. Min Act: -0.0000

Data Index: 1955885 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 5.3233. Min Range: -5.3233

Max Act: 4.3505. Min Act: -0.0000

Data Index: 1345580 (The Pile)

Max Activating Token Index: 321