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

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

Neuron 3700 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: 0.5888. Min Range: -0.5888

Max Act: 0.5530. Min Act: -0.0000

Data Index: 74152 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5888. Min Act: -0.0001

Data Index: 269477 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1285354 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1021841 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5017. Min Act: -0.0000

Data Index: 685890 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4597. Min Act: -0.0001

Data Index: 47777 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4714. Min Act: -0.0000

Data Index: 219514 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4513. Min Act: -0.0000

Data Index: 170696 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4759. Min Act: -0.0000

Data Index: 746344 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4464. Min Act: -0.0000

Data Index: 798895 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4644. Min Act: -0.0001

Data Index: 324552 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4072. Min Act: -0.0000

Data Index: 157470 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4601. Min Act: -0.0001

Data Index: 381288 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4227. Min Act: -0.0001

Data Index: 1003128 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1124226 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4489. Min Act: -0.0000

Data Index: 906104 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4172. Min Act: -0.0001

Data Index: 398906 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1020068 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.3867. Min Act: -0.0001

Data Index: 784642 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.3777. Min Act: -0.0001

Data Index: 125921 (C4 (Web Text))

Max Activating Token Index: 322