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

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

Neuron 1746 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: 0.2609. Min Range: -0.2609

Max Act: 0.2609. Min Act: -0.0001

Data Index: 609086 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1126121 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2213. Min Act: -0.0000

Data Index: 256235 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2011. Min Act: -0.0001

Data Index: 271204 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1957. Min Act: -0.0001

Data Index: 217974 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1922. Min Act: -0.0001

Data Index: 853003 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1807. Min Act: -0.0001

Data Index: 864199 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1735. Min Act: -0.0001

Data Index: 389860 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1742. Min Act: -0.0001

Data Index: 749823 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1672. Min Act: -0.0000

Data Index: 300454 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1677. Min Act: -0.0001

Data Index: 169951 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1669. Min Act: -0.0001

Data Index: 179540 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1646. Min Act: -0.0000

Data Index: 755705 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1637. Min Act: -0.0000

Data Index: 587914 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1699. Min Act: -0.0001

Data Index: 610338 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1697. Min Act: -0.0000

Data Index: 798196 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1637. Min Act: -0.0000

Data Index: 797045 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1738. Min Act: -0.0001

Data Index: 736001 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1726. Min Act: -0.0001

Data Index: 764901 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1661. Min Act: -0.0000

Data Index: 843136 (C4 (Web Text))

Max Activating Token Index: 369