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

Dataset: The Pile

Neuron 360 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: 0.5219. Min Range: -0.5219

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1207405 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1499178 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1913005 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4656. Min Act: -0.0000

Data Index: 111156 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4496. Min Act: -0.0000

Data Index: 909044 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4424. Min Act: -0.0000

Data Index: 689897 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4436. Min Act: -0.0000

Data Index: 944467 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1735138 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1183276 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1770219 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4647. Min Act: -0.0000

Data Index: 279440 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1201932 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1244910 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1112970 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1203464 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4113. Min Act: -0.0000

Data Index: 173130 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1144521 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4059. Min Act: -0.0000

Data Index: 607916 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1261798 (The Pile)

Max Activating Token Index: 732

Text #19

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1292002 (The Pile)

Max Activating Token Index: 193