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

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

Neuron 2388 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: 1.0797. Min Range: -1.0797

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1189474 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9998. Min Act: -0.0001

Data Index: 187995 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8958. Min Act: -0.0001

Data Index: 224849 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9199. Min Act: -0.0001

Data Index: 115163 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1344481 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9966. Min Act: -0.0001

Data Index: 510738 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9289. Min Act: -0.0001

Data Index: 1114085 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8822. Min Act: -0.0001

Data Index: 872036 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1220703 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9118. Min Act: -0.0001

Data Index: 488260 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9304. Min Act: -0.0001

Data Index: 256408 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8232. Min Act: -0.0001

Data Index: 438604 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.7908. Min Act: -0.0001

Data Index: 21020 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8726. Min Act: -0.0001

Data Index: 60956 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8122. Min Act: -0.0001

Data Index: 362481 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1348173 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8461. Min Act: -0.0001

Data Index: 621737 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8909. Min Act: -0.0001

Data Index: 509569 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1307501 (C4 (Web Text))

Max Activating Token Index: 580