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

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

Neuron 274 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6453. Min Range: -2.6453

Max Act: 2.6453. Min Act: -0.0000

Data Index: 1194040 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 2.6453. Min Range: -2.6453

Max Act: 1.7483. Min Act: -0.0000

Data Index: 442976 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 2.6453. Min Range: -2.6453

Max Act: 1.4159. Min Act: -0.0000

Data Index: 714474 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.6453. Min Range: -2.6453

Max Act: 1.1976. Min Act: -0.0000

Data Index: 644691 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.6453. Min Range: -2.6453

Max Act: 1.0311. Min Act: -0.0000

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.8936. Min Act: -0.0000

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.9171. Min Act: -0.0000

Data Index: 363731 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7384. Min Act: -0.0000

Data Index: 894880 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1090513 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.8154. Min Act: -0.0000

Data Index: 800173 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7801. Min Act: -0.0000

Data Index: 588010 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7773. Min Act: -0.0000

Data Index: 722814 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1047065 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7391. Min Act: -0.0000

Data Index: 600455 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7427. Min Act: -0.0000

Data Index: 199822 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7395. Min Act: -0.0000

Data Index: 998086 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1017919 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1292713 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1214745 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 2.6453. Min Range: -2.6453

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1177430 (C4 (Web Text))

Max Activating Token Index: 238