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

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

Neuron 4524 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: 2.9848. Min Range: -2.9848

Max Act: 2.9848. Min Act: -0.0000

Data Index: 1017448 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.7140. Min Act: -0.0000

Data Index: 827499 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.6192. Min Act: -0.0001

Data Index: 640475 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.0174. Min Act: -0.0001

Data Index: 506521 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.2099. Min Act: -0.0001

Data Index: 1344157 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.2196. Min Act: -0.0000

Data Index: 1058168 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.4158. Min Act: -0.0001

Data Index: 582035 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.4185. Min Act: -0.0000

Data Index: 477075 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.4015. Min Act: -0.0000

Data Index: 669286 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.2442. Min Act: -0.0001

Data Index: 53930 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.3718. Min Act: -0.0001

Data Index: 346345 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.1287. Min Act: -0.0000

Data Index: 387877 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.1633. Min Act: -0.0000

Data Index: 269191 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.0042. Min Act: -0.0001

Data Index: 1101976 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.1352. Min Act: -0.0001

Data Index: 154780 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.0008. Min Act: -0.0000

Data Index: 200717 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 2.9848. Min Range: -2.9848

Max Act: 1.9913. Min Act: -0.0000

Data Index: 1344844 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.0148. Min Act: -0.0000

Data Index: 1326250 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.3222. Min Act: -0.0000

Data Index: 548799 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 2.9848. Min Range: -2.9848

Max Act: 2.1028. Min Act: -0.0000

Data Index: 1071889 (C4 (Web Text))

Max Activating Token Index: 662