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

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

Neuron 623 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.7058. Min Act: -0.0000

Data Index: 728465 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1353465 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.5982. Min Act: -0.0000

Data Index: 214564 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.5708. Min Act: -0.0000

Data Index: 615859 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.5138. Min Act: -0.0000

Data Index: 6003 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4914. Min Act: -0.0000

Data Index: 713018 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4665. Min Act: -0.0000

Data Index: 89901 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1167120 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4507. Min Act: -0.0000

Data Index: 54627 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4623. Min Act: -0.0000

Data Index: 770988 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4581. Min Act: -0.0000

Data Index: 390614 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1335342 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4691. Min Act: -0.0000

Data Index: 964657 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1092502 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4392. Min Act: -0.0000

Data Index: 733934 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4289. Min Act: -0.0000

Data Index: 298432 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4328. Min Act: -0.0000

Data Index: 304194 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4352. Min Act: -0.0000

Data Index: 465543 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4477. Min Act: -0.0000

Data Index: 730864 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.7058. Min Range: -0.7058

Max Act: 0.4605. Min Act: -0.0000

Data Index: 972073 (C4 (Web Text))

Max Activating Token Index: 323