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

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

Neuron 4051 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: 2.7199. Min Range: -2.7199

Max Act: 2.7199. Min Act: -0.0000

Data Index: 1303804 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.5459. Min Act: -0.0000

Data Index: 172685 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.2646. Min Act: -0.0000

Data Index: 667235 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.6310. Min Act: -0.0000

Data Index: 1234870 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.3557. Min Act: -0.0000

Data Index: 158622 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.1633. Min Act: -0.0000

Data Index: 327151 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.1371. Min Act: -0.0000

Data Index: 883903 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.2536. Min Act: -0.0000

Data Index: 992204 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.2525. Min Act: -0.0000

Data Index: 352944 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.0864. Min Act: -0.0000

Data Index: 837215 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.0079. Min Act: -0.0000

Data Index: 1294089 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.0235. Min Act: -0.0000

Data Index: 233473 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.8464. Min Act: -0.0000

Data Index: 601815 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.8413. Min Act: -0.0000

Data Index: 955697 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.9314. Min Act: -0.0000

Data Index: 337181 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.8234. Min Act: -0.0000

Data Index: 486705 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 2.7199. Min Range: -2.7199

Max Act: 2.0176. Min Act: -0.0000

Data Index: 1346778 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.9153. Min Act: -0.0000

Data Index: 912003 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.8736. Min Act: -0.0000

Data Index: 235250 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 2.7199. Min Range: -2.7199

Max Act: 1.7612. Min Act: -0.0000

Data Index: 194382 (C4 (Web Text))

Max Activating Token Index: 52