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

Dataset: The Pile

Neuron 1740 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: 5.4912. Min Range: -5.4912

Max Act: 5.3427. Min Act: -0.0000

Data Index: 695301 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 5.4912. Min Range: -5.4912

Max Act: 5.3381. Min Act: -0.0000

Data Index: 1904990 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 5.4912. Min Range: -5.4912

Max Act: 5.4912. Min Act: -0.0000

Data Index: 73646 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 5.4912. Min Range: -5.4912

Max Act: 5.1247. Min Act: -0.0000

Data Index: 236594 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.3972. Min Act: -0.0000

Data Index: 1452726 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.8545. Min Act: -0.0000

Data Index: 1425325 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.6671. Min Act: -0.0000

Data Index: 862782 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.3162. Min Act: -0.0000

Data Index: 240271 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.4645. Min Act: -0.0000

Data Index: 516091 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.5437. Min Act: -0.0000

Data Index: 1668253 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.5167. Min Act: -0.0000

Data Index: 1189728 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.4923. Min Act: -0.0000

Data Index: 622978 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.6312. Min Act: -0.0000

Data Index: 585147 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.0657. Min Act: -0.0000

Data Index: 990383 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.0026. Min Act: -0.0000

Data Index: 417245 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.4306. Min Act: -0.0000

Data Index: 1459208 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.1535. Min Act: -0.0000

Data Index: 1753555 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 5.4912. Min Range: -5.4912

Max Act: 3.9820. Min Act: -0.0000

Data Index: 1657686 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 5.4912. Min Range: -5.4912

Max Act: 4.0060. Min Act: -0.0000

Data Index: 818253 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 5.4912. Min Range: -5.4912

Max Act: 3.6155. Min Act: -0.0000

Data Index: 360647 (The Pile)

Max Activating Token Index: 86