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

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

Neuron 3234 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.7308. Min Act: -0.0000

Data Index: 1768 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.5432. Min Act: -0.0000

Data Index: 667177 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.4170. Min Act: -0.0000

Data Index: 419792 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.5483. Min Act: -0.0000

Data Index: 1086902 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.6458. Min Act: 0.0000

Data Index: 298473 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.1987. Min Act: -0.0000

Data Index: 227781 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.2993. Min Act: 0.0000

Data Index: 1124295 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.0927. Min Act: -0.0000

Data Index: 1145803 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.1687. Min Act: -0.0000

Data Index: 1279012 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.1454. Min Act: -0.0000

Data Index: 194163 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1341430 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9902. Min Act: -0.0000

Data Index: 609124 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.0761. Min Act: 0.0000

Data Index: 302389 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.0776. Min Act: -0.0000

Data Index: 280058 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1045164 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 2.7308. Min Range: -2.7308

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1344188 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9049. Min Act: -0.0000

Data Index: 1304233 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1184667 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9726. Min Act: 0.0002

Data Index: 1114336 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.7308. Min Range: -2.7308

Max Act: 1.9658. Min Act: -0.0000

Data Index: 817337 (C4 (Web Text))

Max Activating Token Index: 948