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

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

Neuron 169 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.5000. Min Act: -0.0000

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.5310. Min Act: 0.0000

Data Index: 1325470 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.5650. Min Act: 0.0000

Data Index: 692258 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.3379. Min Act: 0.0000

Data Index: 214494 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.5073. Min Act: -0.0000

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.3759. Min Act: -0.0000

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.1920. Min Act: -0.0000

Data Index: 673633 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.2557. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.0716. Min Act: -0.0000

Data Index: 707914 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.0314. Min Act: 0.0000

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.5650. Min Range: -2.5650

Max Act: 2.0502. Min Act: 0.0000

Data Index: 50431 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1288913 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.8761. Min Act: -0.0000

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.8244. Min Act: -0.0000

Data Index: 209916 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.6724. Min Act: -0.0000

Data Index: 579495 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.5377. Min Act: -0.0000

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.4750. Min Act: 0.0000

Data Index: 1328641 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.4300. Min Act: -0.0000

Data Index: 914435 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.5066. Min Act: -0.0000

Data Index: 233897 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 2.5650. Min Range: -2.5650

Max Act: 1.4391. Min Act: 0.0000

Data Index: 567604 (C4 (Web Text))

Max Activating Token Index: 383