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

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

Neuron 483 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.2140. Min Act: -0.0002

Data Index: 294033 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8731. Min Act: -0.0002

Data Index: 1135404 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8665. Min Act: -0.0002

Data Index: 665085 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8782. Min Act: -0.0002

Data Index: 268026 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8531. Min Act: -0.0002

Data Index: 1109517 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8108. Min Act: -0.0002

Data Index: 700202 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7783. Min Act: -0.0002

Data Index: 1199095 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7731. Min Act: -0.0002

Data Index: 886702 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7966. Min Act: -0.0002

Data Index: 362166 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7778. Min Act: -0.0002

Data Index: 228410 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7495. Min Act: -0.0002

Data Index: 963731 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7650. Min Act: -0.0002

Data Index: 453570 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7420. Min Act: -0.0002

Data Index: 1288885 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7527. Min Act: -0.0002

Data Index: 259414 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7378. Min Act: -0.0002

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.6783. Min Act: -0.0002

Data Index: 397410 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7861. Min Act: -0.0002

Data Index: 141320 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.6933. Min Act: -0.0002

Data Index: 19900 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7329. Min Act: -0.0002

Data Index: 316870 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.7163. Min Act: -0.0002

Data Index: 961835 (C4 (Web Text))

Max Activating Token Index: 214