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

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

Neuron 5803 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: 5.3254. Min Range: -5.3254

Max Act: 5.3254. Min Act: -0.0000

Data Index: 185260 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 5.3254. Min Range: -5.3254

Max Act: 5.0573. Min Act: -0.0000

Data Index: 669003 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.8075. Min Act: -0.0000

Data Index: 1220154 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.7994. Min Act: -0.0000

Data Index: 284335 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.8103. Min Act: -0.0000

Data Index: 1110588 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.6449. Min Act: -0.0000

Data Index: 1095497 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 5.3254. Min Range: -5.3254

Max Act: 5.0087. Min Act: -0.0000

Data Index: 895167 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.5845. Min Act: -0.0000

Data Index: 947954 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.8134. Min Act: -0.0000

Data Index: 391832 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.6289. Min Act: -0.0000

Data Index: 450054 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.4141. Min Act: -0.0000

Data Index: 596284 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.6471. Min Act: -0.0000

Data Index: 178453 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.2559. Min Act: -0.0000

Data Index: 952009 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.2075. Min Act: -0.0000

Data Index: 1343725 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.3532. Min Act: -0.0000

Data Index: 1589430 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.2621. Min Act: -0.0000

Data Index: 1040190 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.2635. Min Act: -0.0000

Data Index: 305430 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.3734. Min Act: -0.0000

Data Index: 226727 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.1794. Min Act: -0.0000

Data Index: 1351412 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.3254. Min Range: -5.3254

Max Act: 4.1665. Min Act: -0.0000

Data Index: 8714 (C4 (Web Text))

Max Activating Token Index: 109