Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.6815. Min Act: -0.0000

Data Index: 1301349 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.6672. Min Act: -0.0000

Data Index: 1173677 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.5044. Min Act: -0.0000

Data Index: 406269 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.5033. Min Act: -0.0000

Data Index: 915772 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.5941. Min Act: -0.0000

Data Index: 1073542 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.3347. Min Act: -0.0000

Data Index: 1095060 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1224027 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.3700. Min Act: -0.0000

Data Index: 899040 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.4723. Min Act: -0.0000

Data Index: 490905 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.1813. Min Act: -0.0000

Data Index: 1207019 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.6815. Min Range: -2.6815

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1287273 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.1601. Min Act: -0.0000

Data Index: 654319 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.2280. Min Act: -0.0000

Data Index: 187151 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1135723 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.0483. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.1418. Min Act: -0.0000

Data Index: 737680 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.1020. Min Act: -0.0000

Data Index: 370729 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.6815. Min Range: -2.6815

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1064834 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 2.6815. Min Range: -2.6815

Max Act: 1.9873. Min Act: -0.0000

Data Index: 15341 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 2.6815. Min Range: -2.6815

Max Act: 1.7978. Min Act: -0.0000

Data Index: 421483 (C4 (Web Text))

Max Activating Token Index: 447