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

Dataset: The Pile

Neuron 4527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1344156 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1237337 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1242864 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2044. Min Act: -0.0000

Data Index: 974109 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1561342 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1738758 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1942. Min Act: -0.0000

Data Index: 556177 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1777336 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1986. Min Act: 0.0000

Data Index: 613517 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2067. Min Act: -0.0000

Data Index: 166856 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1816652 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1863. Min Act: 0.0000

Data Index: 593694 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1964258 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1951. Min Act: -0.0000

Data Index: 299476 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1880. Min Act: -0.0000

Data Index: 585923 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1937. Min Act: -0.0000

Data Index: 679793 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1873. Min Act: -0.0000

Data Index: 361367 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1160160 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1907. Min Act: 0.0000

Data Index: 1830638 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1685. Min Act: 0.0000

Data Index: 1558167 (The Pile)

Max Activating Token Index: 621