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

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

Neuron 1327 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1453. Min Act: 0.0001

Data Index: 1247712 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1126930 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1263. Min Act: -0.0001

Data Index: 642499 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1233. Min Act: -0.0000

Data Index: 437215 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1158. Min Act: -0.0000

Data Index: 674889 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1033. Min Act: -0.0000

Data Index: 805826 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0971. Min Act: -0.0000

Data Index: 688040 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0926. Min Act: -0.0000

Data Index: 436483 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0921. Min Act: -0.0000

Data Index: 649663 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0910. Min Act: -0.0000

Data Index: 124835 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0866. Min Act: 0.0000

Data Index: 854360 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0842. Min Act: -0.0000

Data Index: 435753 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0871. Min Act: 0.0000

Data Index: 170493 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0835. Min Act: -0.0000

Data Index: 94884 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0835. Min Act: -0.0000

Data Index: 180168 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1024259 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0827. Min Act: -0.0000

Data Index: 873545 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1106084 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0808. Min Act: -0.0000

Data Index: 868376 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.0787. Min Act: 0.0001

Data Index: 452914 (C4 (Web Text))

Max Activating Token Index: 198