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

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

Neuron 2602 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.2911. Min Act: -0.0000

Data Index: 577184 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.2032. Min Act: -0.0000

Data Index: 44190 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.1268. Min Act: -0.0000

Data Index: 616583 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.1065. Min Act: -0.0000

Data Index: 900327 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.0786. Min Act: -0.0000

Data Index: 873818 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9869. Min Act: -0.0000

Data Index: 868766 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1042844 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.2911. Min Range: -1.2911

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1196246 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9924. Min Act: -0.0000

Data Index: 566224 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9164. Min Act: -0.0000

Data Index: 834380 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.8964. Min Act: -0.0000

Data Index: 337170 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1211796 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9072. Min Act: -0.0000

Data Index: 295027 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9344. Min Act: -0.0000

Data Index: 574601 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9253. Min Act: -0.0000

Data Index: 889019 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.8712. Min Act: -0.0000

Data Index: 199436 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1218290 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9165. Min Act: -0.0000

Data Index: 850835 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1075359 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.2911. Min Range: -1.2911

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1294396 (C4 (Web Text))

Max Activating Token Index: 748