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

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

Neuron 3155 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: 2.6318. Min Range: -2.6318

Max Act: 2.6318. Min Act: -0.0000

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 2.6318. Min Range: -2.6318

Max Act: 2.5469. Min Act: -0.0000

Data Index: 653757 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.9614. Min Act: -0.0000

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.8645. Min Act: -0.0000

Data Index: 899406 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.9635. Min Act: -0.0000

Data Index: 1265662 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1145786 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7676. Min Act: -0.0000

Data Index: 407340 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7313. Min Act: -0.0000

Data Index: 476099 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7468. Min Act: -0.0000

Data Index: 270760 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7287. Min Act: -0.0000

Data Index: 236509 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1044132 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7025. Min Act: -0.0000

Data Index: 42490 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.8502. Min Act: -0.0000

Data Index: 1010878 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.7353. Min Act: -0.0000

Data Index: 544798 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.5325. Min Act: -0.0000

Data Index: 341848 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.5258. Min Act: -0.0000

Data Index: 1353726 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.5176. Min Act: -0.0000

Data Index: 808254 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.6002. Min Act: -0.0000

Data Index: 806914 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1079336 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 2.6318. Min Range: -2.6318

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1321991 (C4 (Web Text))

Max Activating Token Index: 792