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

Dataset: The Pile

Neuron 4978 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: 3.6345. Min Range: -3.6345

Max Act: 3.5039. Min Act: -0.0000

Data Index: 177278 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.6345. Min Act: -0.0000

Data Index: 704498 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.2898. Min Act: -0.0000

Data Index: 842509 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.2144. Min Act: -0.0000

Data Index: 1748630 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.1105. Min Act: -0.0000

Data Index: 33598 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.2342. Min Act: -0.0000

Data Index: 1237872 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.3851. Min Act: -0.0000

Data Index: 868695 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.0266. Min Act: -0.0000

Data Index: 239785 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.1444. Min Act: -0.0000

Data Index: 1441347 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.1328. Min Act: -0.0000

Data Index: 987409 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.9664. Min Act: -0.0000

Data Index: 1573806 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.9511. Min Act: -0.0000

Data Index: 1783014 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.9751. Min Act: -0.0000

Data Index: 1361315 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.0546. Min Act: -0.0000

Data Index: 412033 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.0514. Min Act: -0.0000

Data Index: 1010199 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.0249. Min Act: -0.0000

Data Index: 141966 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 3.6345. Min Range: -3.6345

Max Act: 3.0108. Min Act: -0.0000

Data Index: 473804 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.8538. Min Act: -0.0000

Data Index: 1765224 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.9690. Min Act: -0.0000

Data Index: 159672 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 3.6345. Min Range: -3.6345

Max Act: 2.8449. Min Act: -0.0000

Data Index: 281328 (The Pile)

Max Activating Token Index: 65