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

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

Neuron 2609 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.6173. Min Act: -0.0000

Data Index: 802655 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5478. Min Act: -0.0000

Data Index: 77684 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5627. Min Act: -0.0000

Data Index: 544751 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5109. Min Act: -0.0000

Data Index: 279023 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4843. Min Act: -0.0000

Data Index: 845017 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5641. Min Act: -0.0000

Data Index: 304441 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1264197 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4451. Min Act: -0.0000

Data Index: 67038 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.5181. Min Act: -0.0000

Data Index: 837409 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4815. Min Act: -0.0000

Data Index: 842106 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1093757 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4647. Min Act: -0.0000

Data Index: 850201 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4162. Min Act: -0.0000

Data Index: 747239 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4297. Min Act: -0.0000

Data Index: 453794 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4278. Min Act: -0.0000

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1146002 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.3839. Min Act: -0.0000

Data Index: 827810 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4268. Min Act: -0.0000

Data Index: 251003 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.4060. Min Act: -0.0000

Data Index: 627724 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.6173. Min Range: -0.6173

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1020838 (C4 (Web Text))

Max Activating Token Index: 552