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

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

Neuron 951 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.3035. Min Act: -0.0001

Data Index: 622638 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1965. Min Act: -0.0001

Data Index: 1225737 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.9771. Min Act: -0.0001

Data Index: 493857 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7706. Min Act: -0.0001

Data Index: 999249 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7524. Min Act: -0.0001

Data Index: 754909 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7421. Min Act: -0.0001

Data Index: 935845 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7143. Min Act: -0.0000

Data Index: 964284 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7046. Min Act: -0.0001

Data Index: 379564 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6930. Min Act: -0.0001

Data Index: 193012 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6932. Min Act: -0.0001

Data Index: 782100 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.7359. Min Act: -0.0000

Data Index: 150855 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6743. Min Act: -0.0000

Data Index: 490946 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6625. Min Act: -0.0001

Data Index: 227095 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6617. Min Act: -0.0001

Data Index: 829778 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6176. Min Act: -0.0001

Data Index: 254256 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6682. Min Act: -0.0000

Data Index: 648660 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1031996 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6483. Min Act: -0.0001

Data Index: 981432 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6007. Min Act: -0.0001

Data Index: 937646 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 1.3035. Min Range: -1.3035

Max Act: 0.6228. Min Act: -0.0001

Data Index: 287628 (C4 (Web Text))

Max Activating Token Index: 916