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

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

Neuron 2851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.3865. Min Act: -0.0001

Data Index: 217195 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.3906. Min Act: -0.0001

Data Index: 1228528 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2823. Min Act: -0.0001

Data Index: 964148 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2015. Min Act: -0.0001

Data Index: 828013 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2768. Min Act: -0.0001

Data Index: 225672 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1549. Min Act: -0.0001

Data Index: 216682 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1547. Min Act: -0.0001

Data Index: 1256648 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2477. Min Act: -0.0001

Data Index: 552688 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.3014. Min Act: -0.0001

Data Index: 1343102 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2580. Min Act: -0.0001

Data Index: 669222 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2828. Min Act: -0.0001

Data Index: 1048818 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2238. Min Act: -0.0001

Data Index: 285168 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1595. Min Act: -0.0001

Data Index: 240344 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1900. Min Act: -0.0001

Data Index: 366087 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1726. Min Act: -0.0001

Data Index: 185514 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1110617 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2337. Min Act: -0.0001

Data Index: 720113 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1645. Min Act: -0.0001

Data Index: 762311 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2205. Min Act: -0.0001

Data Index: 587254 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.2166. Min Act: -0.0001

Data Index: 266903 (C4 (Web Text))

Max Activating Token Index: 421