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

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

Neuron 4801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.1163. Min Act: -0.0000

Data Index: 77090 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2205. Min Act: -0.0000

Data Index: 538450 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.0480. Min Act: -0.0000

Data Index: 426194 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.8648. Min Act: -0.0000

Data Index: 909059 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.0479. Min Act: -0.0000

Data Index: 91052 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.6475. Min Act: -0.0000

Data Index: 1203918 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.9807. Min Act: -0.0000

Data Index: 1874 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.5097. Min Act: -0.0000

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.4975. Min Act: -0.0000

Data Index: 494837 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 4.4975. Min Range: -4.4975

Max Act: 4.2541. Min Act: -0.0000

Data Index: 24051 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.7421. Min Act: -0.0000

Data Index: 910097 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.7579. Min Act: -0.0000

Data Index: 609627 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.5726. Min Act: -0.0000

Data Index: 503679 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.8745. Min Act: -0.0000

Data Index: 686920 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.6946. Min Act: -0.0000

Data Index: 1055600 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.4744. Min Act: -0.0000

Data Index: 939453 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.6493. Min Act: -0.0000

Data Index: 258132 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.8158. Min Act: -0.0000

Data Index: 899774 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.7830. Min Act: -0.0000

Data Index: 1202726 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 4.4975. Min Range: -4.4975

Max Act: 3.7604. Min Act: -0.0000

Data Index: 1051458 (C4 (Web Text))

Max Activating Token Index: 525