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

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

Neuron 4222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0000

Data Index: 311565 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1303864 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1299. Min Act: -0.0000

Data Index: 771690 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1233. Min Act: -0.0000

Data Index: 314510 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1157. Min Act: -0.0000

Data Index: 294396 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1190. Min Act: -0.0000

Data Index: 39759 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1191. Min Act: -0.0000

Data Index: 22851 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1206. Min Act: -0.0000

Data Index: 562646 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1068. Min Act: -0.0000

Data Index: 63554 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1306582 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1358096 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1046. Min Act: -0.0000

Data Index: 928566 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1033. Min Act: -0.0000

Data Index: 591575 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1046. Min Act: -0.0000

Data Index: 815036 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1014. Min Act: -0.0000

Data Index: 400621 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1032. Min Act: -0.0000

Data Index: 247727 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1155291 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0971. Min Act: -0.0000

Data Index: 852835 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1000. Min Act: -0.0000

Data Index: 288584 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0954. Min Act: -0.0000

Data Index: 108436 (C4 (Web Text))

Max Activating Token Index: 772