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

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

Neuron 1426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.7256. Min Act: -0.0000

Data Index: 74080 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6344. Min Act: -0.0001

Data Index: 898147 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6130. Min Act: -0.0001

Data Index: 857315 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5797. Min Act: -0.0001

Data Index: 438217 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6327. Min Act: -0.0001

Data Index: 610377 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6023. Min Act: -0.0001

Data Index: 6658 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5929. Min Act: -0.0001

Data Index: 1118028 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5889. Min Act: -0.0001

Data Index: 888869 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5923. Min Act: -0.0000

Data Index: 389322 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6076. Min Act: -0.0000

Data Index: 530937 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5870. Min Act: -0.0001

Data Index: 272368 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6017. Min Act: -0.0001

Data Index: 607969 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5601. Min Act: -0.0000

Data Index: 312458 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1101088 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1129787 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5272. Min Act: -0.0001

Data Index: 208747 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5818. Min Act: -0.0000

Data Index: 376421 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5228. Min Act: -0.0001

Data Index: 208995 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5272. Min Act: -0.0001

Data Index: 9328 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5073. Min Act: -0.0000

Data Index: 880264 (C4 (Web Text))

Max Activating Token Index: 1000