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

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

Neuron 2128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1569395 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1601232 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1184101 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6152. Min Act: -0.0001

Data Index: 1364518 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1577783 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6174. Min Act: -0.0001

Data Index: 1602283 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1479962 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1378081 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1640365 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1652548 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6038. Min Act: -0.0001

Data Index: 50303 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5987. Min Act: -0.0001

Data Index: 1635756 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5684. Min Act: -0.0001

Data Index: 1536594 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5720. Min Act: -0.0001

Data Index: 1512738 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1643075 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1378829 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5686. Min Act: -0.0001

Data Index: 1505883 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5578. Min Act: -0.0001

Data Index: 1013051 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5598. Min Act: -0.0001

Data Index: 1531181 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1503706 (Python Code)

Max Activating Token Index: 163