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

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

Neuron 665 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: 4.4484. Min Range: -4.4484

Max Act: 4.4484. Min Act: -0.0000

Data Index: 477134 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 4.4484. Min Range: -4.4484

Max Act: 4.0758. Min Act: -0.0000

Data Index: 1206311 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 4.4484. Min Range: -4.4484

Max Act: 4.2230. Min Act: -0.0000

Data Index: 834141 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.9839. Min Act: -0.0000

Data Index: 749960 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.9517. Min Act: -0.0000

Data Index: 697658 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 4.4484. Min Range: -4.4484

Max Act: 4.0019. Min Act: -0.0000

Data Index: 979666 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 4.4484. Min Range: -4.4484

Max Act: 4.1121. Min Act: -0.0000

Data Index: 1107389 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 4.4484. Min Range: -4.4484

Max Act: 4.0424. Min Act: -0.0000

Data Index: 553579 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.7414. Min Act: -0.0000

Data Index: 523477 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.7441. Min Act: -0.0000

Data Index: 505959 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.7127. Min Act: -0.0000

Data Index: 1311224 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.6476. Min Act: -0.0000

Data Index: 1239361 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.5644. Min Act: -0.0000

Data Index: 545404 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.3342. Min Act: -0.0000

Data Index: 549397 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.3182. Min Act: -0.0000

Data Index: 918525 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.2674. Min Act: -0.0000

Data Index: 1056034 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.1000. Min Act: -0.0000

Data Index: 1036735 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 4.4484. Min Range: -4.4484

Max Act: 3.1227. Min Act: -0.0000

Data Index: 554982 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 4.4484. Min Range: -4.4484

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1528141 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 4.4484. Min Range: -4.4484

Max Act: 2.6141. Min Act: -0.0000

Data Index: 1391027 (Python Code)

Max Activating Token Index: 259