Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 225 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1244940 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.8184. Min Act: -0.0000

Data Index: 504411 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.8067. Min Act: -0.0000

Data Index: 967519 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.4972. Min Act: -0.0000

Data Index: 862147 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.3185. Min Act: -0.0000

Data Index: 120357 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.3247. Min Act: -0.0000

Data Index: 1089230 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.1294. Min Act: -0.0000

Data Index: 666478 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1066854 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.1033. Min Act: -0.0000

Data Index: 821191 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.2273. Min Act: -0.0000

Data Index: 962805 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.2127. Min Act: -0.0000

Data Index: 1119994 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.1477. Min Act: -0.0000

Data Index: 32246 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.0741. Min Act: -0.0000

Data Index: 391796 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 2.9615. Min Range: -2.9615

Max Act: 1.9698. Min Act: -0.0000

Data Index: 902028 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 2.9615. Min Range: -2.9615

Max Act: 1.9896. Min Act: -0.0000

Data Index: 983344 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1258104 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.0423. Min Act: -0.0000

Data Index: 267661 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.9615. Min Range: -2.9615

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1001634 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.9615. Min Range: -2.9615

Max Act: 1.8992. Min Act: -0.0000

Data Index: 533972 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 2.9615. Min Range: -2.9615

Max Act: 1.9891. Min Act: -0.0000

Data Index: 635906 (C4 (Web Text))

Max Activating Token Index: 322