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

Dataset: The Pile

Neuron 2334 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1538226 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1671790 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5159. Min Act: -0.0000

Data Index: 793385 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1851011 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1076630 (The Pile)

Max Activating Token Index: 291

Text #5

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1239543 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4045. Min Act: 0.0000

Data Index: 375410 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1124939 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1459442 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3809. Min Act: -0.0000

Data Index: 978955 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3535. Min Act: -0.0000

Data Index: 28386 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3497. Min Act: -0.0000

Data Index: 750635 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3523. Min Act: -0.0000

Data Index: 269077 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1982707 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1413998 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3315. Min Act: -0.0000

Data Index: 610151 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.2984. Min Act: -0.0000

Data Index: 621759 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1091190 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.2772. Min Act: -0.0000

Data Index: 392524 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.2900. Min Act: -0.0000

Data Index: 195286 (The Pile)

Max Activating Token Index: 993