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

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

Neuron 1467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4100. Min Act: -0.0000

Data Index: 345869 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2705. Min Act: -0.0000

Data Index: 16636 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.5125. Min Act: -0.0000

Data Index: 1143400 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.4050. Min Act: -0.0000

Data Index: 977619 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1169925 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2293. Min Act: -0.0000

Data Index: 819700 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2513. Min Act: -0.0000

Data Index: 332359 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2211. Min Act: -0.0000

Data Index: 855870 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1632. Min Act: -0.0000

Data Index: 218488 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2640. Min Act: -0.0000

Data Index: 343041 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1880. Min Act: -0.0000

Data Index: 438953 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1743. Min Act: -0.0000

Data Index: 838086 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1087. Min Act: -0.0000

Data Index: 237761 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1178372 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1199907 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.0922. Min Act: -0.0000

Data Index: 200567 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2250. Min Act: -0.0000

Data Index: 1224426 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1293017 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.2056. Min Act: -0.0000

Data Index: 631472 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.5125. Min Range: -1.5125

Max Act: 1.1362. Min Act: -0.0000

Data Index: 586026 (C4 (Web Text))

Max Activating Token Index: 775