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

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

Neuron 5366 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7926. Min Act: -0.0000

Data Index: 441450 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7131. Min Act: -0.0000

Data Index: 151166 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1224544 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6140. Min Act: -0.0000

Data Index: 349577 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5783. Min Act: -0.0000

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4913. Min Act: -0.0000

Data Index: 6293 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5404. Min Act: -0.0000

Data Index: 595037 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4670. Min Act: -0.0000

Data Index: 827918 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1150450 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5222. Min Act: -0.0000

Data Index: 3122 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5221. Min Act: -0.0000

Data Index: 117941 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5271. Min Act: -0.0000

Data Index: 763027 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1214841 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4998. Min Act: -0.0000

Data Index: 265974 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1206090 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4814. Min Act: -0.0000

Data Index: 742092 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4834. Min Act: -0.0000

Data Index: 952397 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4819. Min Act: -0.0000

Data Index: 220568 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1074320 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.4657. Min Act: -0.0000

Data Index: 389704 (C4 (Web Text))

Max Activating Token Index: 953