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

Dataset: The Pile

Neuron 786 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: 0.8760. Min Range: -0.8760

Max Act: 0.8760. Min Act: -0.0000

Data Index: 540751 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1405065 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7551. Min Act: -0.0000

Data Index: 364028 (The Pile)

Max Activating Token Index: 45

Text #3

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1119549 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7575. Min Act: -0.0000

Data Index: 652099 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1275714 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8437. Min Act: -0.0000

Data Index: 484819 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1322694 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6454. Min Act: -0.0000

Data Index: 990268 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1714419 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1355099 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1257804 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1867283 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1822224 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6391. Min Act: -0.0000

Data Index: 418350 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6533. Min Act: -0.0000

Data Index: 291882 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1510019 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1602126 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1204086 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6466. Min Act: -0.0000

Data Index: 72701 (The Pile)

Max Activating Token Index: 358