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

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

Neuron 663 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: 1.5820. Min Range: -1.5820

Max Act: 1.5217. Min Act: -0.0000

Data Index: 510567 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1226131 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1289331 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1108405 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1168432 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1439415 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1491457 (Python Code)

Max Activating Token Index: 702

Text #7

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4777. Min Act: -0.0000

Data Index: 697793 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1115599 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1480989 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1617606 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3599. Min Act: -0.0000

Data Index: 541067 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1451821 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1159766 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1555110 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1035637 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1616046 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3882. Min Act: -0.0000

Data Index: 1572316 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1486782 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4518. Min Act: -0.0000

Data Index: 886509 (C4 (Web Text))

Max Activating Token Index: 155