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

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

Neuron 858 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: 2.4249. Min Range: -2.4249

Max Act: 2.4249. Min Act: -0.0000

Data Index: 1115936 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.1739. Min Act: -0.0000

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.1002. Min Act: -0.0000

Data Index: 418756 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.2670. Min Act: -0.0000

Data Index: 1093001 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.0072. Min Act: -0.0000

Data Index: 117362 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.9906. Min Act: -0.0000

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.0194. Min Act: -0.0000

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.9001. Min Act: -0.0000

Data Index: 112792 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.9219. Min Act: -0.0000

Data Index: 1347802 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8951. Min Act: -0.0000

Data Index: 204341 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8906. Min Act: -0.0000

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8961. Min Act: -0.0000

Data Index: 1393964 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.9320. Min Act: -0.0000

Data Index: 818691 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 2.4249. Min Range: -2.4249

Max Act: 2.0297. Min Act: -0.0000

Data Index: 709120 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.9256. Min Act: -0.0000

Data Index: 1356549 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.6970. Min Act: -0.0000

Data Index: 166436 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8431. Min Act: -0.0000

Data Index: 64604 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8316. Min Act: -0.0000

Data Index: 598616 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8635. Min Act: -0.0000

Data Index: 147290 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 2.4249. Min Range: -2.4249

Max Act: 1.8097. Min Act: -0.0000

Data Index: 1233599 (C4 (Web Text))

Max Activating Token Index: 909