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

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

Neuron 2338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1200933 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1303761 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0746. Min Act: -0.0002

Data Index: 697624 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0740. Min Act: -0.0002

Data Index: 476616 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0728. Min Act: -0.0002

Data Index: 377375 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1084145 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1207221 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0654. Min Act: -0.0002

Data Index: 892960 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0671. Min Act: -0.0002

Data Index: 694633 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1029395 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0626. Min Act: -0.0002

Data Index: 528654 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1079212 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1193555 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1253530 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0612. Min Act: -0.0002

Data Index: 984927 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0583. Min Act: -0.0002

Data Index: 804949 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0606. Min Act: -0.0002

Data Index: 243152 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0606. Min Act: -0.0002

Data Index: 169301 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0600. Min Act: -0.0002

Data Index: 794832 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0619. Min Act: -0.0002

Data Index: 706510 (C4 (Web Text))

Max Activating Token Index: 457