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

Dataset: The Pile

Neuron 3366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1755785 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.7346. Min Act: -0.0000

Data Index: 1839695 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.8348. Min Act: -0.0000

Data Index: 916936 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1806481 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5422. Min Act: -0.0000

Data Index: 218738 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5968. Min Act: -0.0000

Data Index: 1506716 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1486094 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5532. Min Act: -0.0000

Data Index: 1145281 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1369389 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4599. Min Act: -0.0000

Data Index: 521978 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5722. Min Act: -0.0000

Data Index: 26507 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4810. Min Act: -0.0000

Data Index: 429726 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1706821 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1206460 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1307424 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4159. Min Act: -0.0000

Data Index: 443959 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1992768 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3658. Min Act: -0.0000

Data Index: 235857 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1884814 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1798975 (The Pile)

Max Activating Token Index: 960