Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 516 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1162517 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2635. Min Act: -0.0001

Data Index: 492493 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2515. Min Act: -0.0001

Data Index: 862241 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2513. Min Act: -0.0001

Data Index: 923935 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2655. Min Act: -0.0001

Data Index: 488232 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2216. Min Act: -0.0001

Data Index: 685259 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1161680 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1071488 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2292. Min Act: -0.0001

Data Index: 1249445 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2222. Min Act: -0.0001

Data Index: 565597 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1150099 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2500. Min Act: -0.0001

Data Index: 830975 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2221. Min Act: -0.0001

Data Index: 550723 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1330908 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1269138 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2212. Min Act: -0.0001

Data Index: 4551 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2273. Min Act: -0.0001

Data Index: 410615 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1222651 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2334. Min Act: -0.0001

Data Index: 208055 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.2655. Min Range: -0.2655

Max Act: 0.2244. Min Act: -0.0001

Data Index: 673335 (C4 (Web Text))

Max Activating Token Index: 793