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

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

Neuron 5042 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4626. Min Act: -0.0000

Data Index: 752938 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.5073. Min Act: -0.0000

Data Index: 419391 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3779. Min Act: -0.0000

Data Index: 279139 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.4061. Min Act: 0.0000

Data Index: 781944 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2256. Min Act: -0.0000

Data Index: 782776 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.3396. Min Act: 0.0000

Data Index: 366990 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1184689 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.2756. Min Act: 0.0000

Data Index: 1043960 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.1521. Min Act: 0.0000

Data Index: 229634 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1205221 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0668. Min Act: 0.0000

Data Index: 206931 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0283. Min Act: -0.0000

Data Index: 502490 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0540. Min Act: -0.0000

Data Index: 64176 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.1349. Min Act: -0.0000

Data Index: 190 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0999. Min Act: -0.0000

Data Index: 331730 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0536. Min Act: -0.0000

Data Index: 841597 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0821. Min Act: -0.0000

Data Index: 729335 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1287202 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0032. Min Act: -0.0000

Data Index: 722360 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.5073. Min Range: -1.5073

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1267052 (C4 (Web Text))

Max Activating Token Index: 757