Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.7624. Min Act: -0.0002

Data Index: 609546 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.4154. Min Act: -0.0002

Data Index: 548036 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.3099. Min Act: -0.0002

Data Index: 638169 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.3959. Min Act: -0.0002

Data Index: 141720 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.2708. Min Act: -0.0002

Data Index: 109406 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.3820. Min Act: -0.0002

Data Index: 958052 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.0017. Min Act: -0.0002

Data Index: 3918 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.4534. Min Act: -0.0002

Data Index: 1049257 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.3341. Min Act: -0.0002

Data Index: 1109164 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.2091. Min Act: -0.0002

Data Index: 391569 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.3202. Min Act: -0.0002

Data Index: 97886 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.2346. Min Act: -0.0002

Data Index: 411600 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.0969. Min Act: -0.0002

Data Index: 262633 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.1506. Min Act: -0.0002

Data Index: 34811 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.0546. Min Act: -0.0002

Data Index: 1288105 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.2360. Min Act: -0.0002

Data Index: 450294 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 1.7624. Min Range: -1.7624

Max Act: 0.9815. Min Act: -0.0002

Data Index: 403122 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.0847. Min Act: -0.0002

Data Index: 1170008 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.1799. Min Act: -0.0002

Data Index: 1285485 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.7624. Min Range: -1.7624

Max Act: 1.2128. Min Act: -0.0002

Data Index: 563912 (C4 (Web Text))

Max Activating Token Index: 795