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

Dataset: The Pile

Neuron 1240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2731. Min Act: -0.0000

Data Index: 810658 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1503. Min Act: -0.0000

Data Index: 497303 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1439539 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.5518. Min Act: -0.0000

Data Index: 32914 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1272433 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0472. Min Act: -0.0000

Data Index: 242292 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1658. Min Act: -0.0000

Data Index: 820167 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1498248 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1018. Min Act: -0.0000

Data Index: 473707 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1052. Min Act: -0.0000

Data Index: 718827 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1854291 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1649. Min Act: -0.0000

Data Index: 386056 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1901203 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1456716 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.2114. Min Act: -0.0000

Data Index: 252442 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1607301 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0796. Min Act: -0.0000

Data Index: 1419912 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1283793 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.5518. Min Range: -1.5518

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1687209 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 1.5518. Min Range: -1.5518

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1739307 (The Pile)

Max Activating Token Index: 905