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

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

Neuron 1202 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6606. Min Act: 0.0000

Data Index: 152397 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6064. Min Act: 0.0000

Data Index: 1221877 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1129548 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5254. Min Act: -0.0000

Data Index: 45198 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5161. Min Act: -0.0000

Data Index: 407875 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4798. Min Act: 0.0003

Data Index: 179681 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4958. Min Act: -0.0000

Data Index: 112655 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4921. Min Act: 0.0000

Data Index: 863839 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4762. Min Act: -0.0000

Data Index: 612670 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4618. Min Act: -0.0000

Data Index: 924358 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4671. Min Act: 0.0000

Data Index: 898983 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4245. Min Act: 0.0000

Data Index: 55791 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1111634 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4235. Min Act: 0.0000

Data Index: 167437 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4053. Min Act: -0.0000

Data Index: 791684 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4316. Min Act: 0.0001

Data Index: 1235151 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4062. Min Act: 0.0001

Data Index: 1097557 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4197. Min Act: 0.0000

Data Index: 877948 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4159. Min Act: -0.0000

Data Index: 296583 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4131. Min Act: 0.0002

Data Index: 554018 (C4 (Web Text))

Max Activating Token Index: 55