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

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

Neuron 2641 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2398. Min Act: -0.0000

Data Index: 404258 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1954. Min Act: -0.0000

Data Index: 483248 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1381. Min Act: -0.0000

Data Index: 635578 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1123128 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1310. Min Act: -0.0000

Data Index: 243081 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1115. Min Act: -0.0000

Data Index: 205348 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1308221 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1087125 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0994. Min Act: -0.0000

Data Index: 257957 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0917. Min Act: -0.0000

Data Index: 639969 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1005. Min Act: -0.0000

Data Index: 542945 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0992. Min Act: -0.0000

Data Index: 177767 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0970. Min Act: -0.0000

Data Index: 788587 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0972. Min Act: -0.0000

Data Index: 937465 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1137471 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1265624 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0917. Min Act: -0.0000

Data Index: 812753 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0965. Min Act: 0.0000

Data Index: 782149 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0864. Min Act: -0.0000

Data Index: 370721 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.0884. Min Act: -0.0000

Data Index: 168607 (C4 (Web Text))

Max Activating Token Index: 138