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

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

Neuron 71 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.0001

Data Index: 584424 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.3673. Min Act: -0.0001

Data Index: 180606 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.9526. Min Act: -0.0001

Data Index: 279210 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.1376. Min Act: -0.0001

Data Index: 1147615 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.3171. Min Act: -0.0001

Data Index: 441764 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.2504. Min Act: -0.0001

Data Index: 78097 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.8366. Min Act: -0.0001

Data Index: 647733 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.1926. Min Act: -0.0001

Data Index: 455613 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.9105. Min Act: -0.0000

Data Index: 899469 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.9113. Min Act: -0.0001

Data Index: 594297 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.0471. Min Act: -0.0001

Data Index: 93289 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.8659. Min Act: -0.0001

Data Index: 558894 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.4772. Min Act: -0.0001

Data Index: 885021 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.8207. Min Act: -0.0001

Data Index: 510901 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.8136. Min Act: -0.0001

Data Index: 932944 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.6133. Min Act: -0.0001

Data Index: 221403 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.5709. Min Act: -0.0001

Data Index: 462043 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.3394. Min Act: -0.0001

Data Index: 890778 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.0307. Min Act: -0.0001

Data Index: 302889 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 5.9743. Min Range: -5.9743

Max Act: 4.4792. Min Act: -0.0001

Data Index: 913921 (C4 (Web Text))

Max Activating Token Index: 499