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

Dataset: The Pile

Neuron 3618 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: 0.4622. Min Range: -0.4622

Max Act: 0.4622. Min Act: -0.0000

Data Index: 774931 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1889812 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3888. Min Act: -0.0000

Data Index: 612694 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1761879 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3734. Min Act: -0.0000

Data Index: 128670 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3516. Min Act: 0.0000

Data Index: 516511 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3698. Min Act: 0.0000

Data Index: 1478166 (The Pile)

Max Activating Token Index: 780

Text #7

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1158856 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3483. Min Act: 0.0001

Data Index: 1592478 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1586641 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1375766 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1134524 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3534. Min Act: -0.0000

Data Index: 386506 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3354. Min Act: -0.0001

Data Index: 944252 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3381. Min Act: -0.0000

Data Index: 462393 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3378. Min Act: 0.0000

Data Index: 1303820 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3577. Min Act: -0.0000

Data Index: 413707 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1763083 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3415. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3299. Min Act: -0.0000

Data Index: 554475 (The Pile)

Max Activating Token Index: 278