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

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

Neuron 3699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.2191. Min Act: -0.0001

Data Index: 556073 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.1571. Min Act: -0.0000

Data Index: 11527 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.1626. Min Act: -0.0001

Data Index: 975227 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0369. Min Act: -0.0000

Data Index: 740890 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1257724 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1122995 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9269. Min Act: -0.0001

Data Index: 253947 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8774. Min Act: -0.0001

Data Index: 841420 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1343008 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1268281 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8385. Min Act: -0.0000

Data Index: 283715 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8012. Min Act: -0.0000

Data Index: 110495 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8128. Min Act: -0.0000

Data Index: 427181 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1022205 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8842. Min Act: -0.0000

Data Index: 855849 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7997. Min Act: -0.0000

Data Index: 747829 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7589. Min Act: -0.0001

Data Index: 238798 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7696. Min Act: -0.0000

Data Index: 3041 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7903. Min Act: -0.0000

Data Index: 608141 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1246335 (C4 (Web Text))

Max Activating Token Index: 696