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

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

Neuron 3612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.3058. Min Act: -0.0001

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.4661. Min Act: -0.0001

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.3069. Min Act: -0.0001

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.2428. Min Act: -0.0001

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.2154. Min Act: -0.0001

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.1233. Min Act: -0.0001

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.1134. Min Act: -0.0001

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.0839. Min Act: -0.0001

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.0784. Min Act: -0.0001

Data Index: 481047 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.1972. Min Act: -0.0001

Data Index: 966695 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.0265. Min Act: -0.0001

Data Index: 371767 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.0051. Min Act: -0.0001

Data Index: 953865 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 3.4661. Min Range: -3.4661

Max Act: 3.0156. Min Act: -0.0001

Data Index: 594020 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.9788. Min Act: -0.0001

Data Index: 671486 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.9175. Min Act: -0.0001

Data Index: 984261 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.4306. Min Act: -0.0001

Data Index: 546552 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.6229. Min Act: -0.0001

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.5107. Min Act: -0.0001

Data Index: 939170 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.6876. Min Act: -0.0001

Data Index: 638722 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 3.4661. Min Range: -3.4661

Max Act: 2.2726. Min Act: -0.0001

Data Index: 150372 (C4 (Web Text))

Max Activating Token Index: 828