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

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

Neuron 1595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6976. Min Act: -0.0001

Data Index: 1188148 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3812. Min Act: -0.0001

Data Index: 98673 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3683. Min Act: -0.0001

Data Index: 775425 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3871. Min Act: -0.0001

Data Index: 578581 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1787. Min Act: -0.0001

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1152. Min Act: -0.0001

Data Index: 1089620 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0766. Min Act: -0.0001

Data Index: 666488 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1455. Min Act: -0.0001

Data Index: 73872 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1162. Min Act: -0.0001

Data Index: 695804 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1693. Min Act: -0.0001

Data Index: 377787 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1639. Min Act: -0.0001

Data Index: 446063 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1327335 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1868. Min Act: -0.0001

Data Index: 327813 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.6976. Min Range: -1.6976

Max Act: 0.9954. Min Act: -0.0001

Data Index: 1029566 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0768. Min Act: -0.0001

Data Index: 69779 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0131. Min Act: -0.0001

Data Index: 456623 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0668. Min Act: -0.0001

Data Index: 434991 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0578. Min Act: -0.0001

Data Index: 1032313 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0165. Min Act: -0.0001

Data Index: 1227667 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.0739. Min Act: -0.0001

Data Index: 1101421 (C4 (Web Text))

Max Activating Token Index: 852