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

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

Neuron 2728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1580104 (Python Code)

Max Activating Token Index: 550

Text #1

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1648377 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1565318 (Python Code)

Max Activating Token Index: 569

Text #3

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1537523 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1549566 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1394542 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9293. Min Act: -0.0000

Data Index: 255321 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9447. Min Act: -0.0000

Data Index: 73726 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1034467 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8862. Min Act: -0.0000

Data Index: 576768 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8767. Min Act: -0.0000

Data Index: 290300 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8672. Min Act: -0.0000

Data Index: 335104 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8275. Min Act: -0.0000

Data Index: 461065 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1423752 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1432590 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1408371 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.7962. Min Act: -0.0000

Data Index: 71213 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1108611 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1450603 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8307. Min Act: -0.0000

Data Index: 770713 (C4 (Web Text))

Max Activating Token Index: 998