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

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

Neuron 3603 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: 0.7555. Min Range: -0.7555

Max Act: 0.7555. Min Act: -0.0000

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.7338. Min Act: -0.0000

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6712. Min Act: -0.0000

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1117643 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6724. Min Act: -0.0000

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6355. Min Act: -0.0000

Data Index: 416832 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6509. Min Act: -0.0000

Data Index: 401468 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6271. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6203. Min Act: -0.0000

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.6085. Min Act: -0.0000

Data Index: 916987 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5099. Min Act: -0.0001

Data Index: 99209 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1311515 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5638. Min Act: -0.0000

Data Index: 509141 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.4896. Min Act: -0.0000

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.4920. Min Act: -0.0001

Data Index: 953009 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5195. Min Act: -0.0000

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.5012. Min Act: -0.0000

Data Index: 342630 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.4714. Min Act: -0.0000

Data Index: 72910 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.4266. Min Act: -0.0000

Data Index: 2620 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.7555. Min Range: -0.7555

Max Act: 0.4343. Min Act: -0.0000

Data Index: 179165 (C4 (Web Text))

Max Activating Token Index: 1006