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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 623 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.6320. Min Act: -0.0000

Data Index: 436747 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5599. Min Act: -0.0000

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.5404. Min Act: -0.0001

Data Index: 995249 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1155515 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4739. Min Act: -0.0000

Data Index: 60041 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4329. Min Act: -0.0000

Data Index: 924196 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4070. Min Act: -0.0001

Data Index: 863856 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4223. Min Act: -0.0001

Data Index: 885421 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.4060. Min Act: -0.0000

Data Index: 196200 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3968. Min Act: -0.0001

Data Index: 165957 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3803. Min Act: -0.0000

Data Index: 882488 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3603. Min Act: -0.0000

Data Index: 825165 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3603. Min Act: -0.0001

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3389. Min Act: -0.0001

Data Index: 1269634 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3233. Min Act: -0.0000

Data Index: 608662 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3391. Min Act: -0.0000

Data Index: 627766 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.2681. Min Act: -0.0001

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.2928. Min Act: -0.0001

Data Index: 914517 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.2696. Min Act: -0.0000

Data Index: 573831 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.6320. Min Range: -0.6320

Max Act: 0.3412. Min Act: -0.0000

Data Index: 570778 (C4 (Web Text))

Max Activating Token Index: 653