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

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

Neuron 4184 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: 0.2079. Min Range: -0.2079

Max Act: 0.2079. Min Act: -0.0001

Data Index: 892837 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1429. Min Act: -0.0001

Data Index: 792194 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1117928 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1150722 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1195. Min Act: -0.0001

Data Index: 623770 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1166. Min Act: -0.0001

Data Index: 259714 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1042. Min Act: -0.0001

Data Index: 597583 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1131. Min Act: -0.0000

Data Index: 223175 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1042340 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1388572 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0983. Min Act: -0.0000

Data Index: 185854 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1145. Min Act: -0.0001

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1425980 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1166638 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0994. Min Act: -0.0001

Data Index: 575756 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1131793 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0943. Min Act: -0.0001

Data Index: 273182 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1648309 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0974. Min Act: -0.0001

Data Index: 386676 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.2079. Min Range: -0.2079

Max Act: 0.0897. Min Act: -0.0001

Data Index: 837948 (C4 (Web Text))

Max Activating Token Index: 787