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

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

Neuron 2130 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: 2.5461. Min Range: -2.5461

Max Act: 2.5461. Min Act: -0.0000

Data Index: 402250 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1323189 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.2980. Min Act: -0.0000

Data Index: 663927 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.2164. Min Act: -0.0001

Data Index: 431608 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.1207. Min Act: -0.0000

Data Index: 116864 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.0748. Min Act: -0.0001

Data Index: 448592 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.0278. Min Act: -0.0000

Data Index: 393086 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.3074. Min Act: -0.0001

Data Index: 1169655 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.2242. Min Act: -0.0001

Data Index: 1097619 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.0533. Min Act: -0.0001

Data Index: 1315525 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.9225. Min Act: -0.0000

Data Index: 320635 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.7890. Min Act: -0.0001

Data Index: 1012476 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.5461. Min Range: -2.5461

Max Act: 2.2722. Min Act: -0.0000

Data Index: 71554 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.9384. Min Act: -0.0001

Data Index: 685464 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.9998. Min Act: -0.0001

Data Index: 569490 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.9088. Min Act: -0.0001

Data Index: 1133593 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.8812. Min Act: -0.0000

Data Index: 725702 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.8749. Min Act: -0.0000

Data Index: 277790 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.8398. Min Act: -0.0001

Data Index: 776844 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 2.5461. Min Range: -2.5461

Max Act: 1.8492. Min Act: -0.0001

Data Index: 302715 (C4 (Web Text))

Max Activating Token Index: 150