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

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

Neuron 3027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.8202. Min Range: -9.8202

Max Act: 9.8202. Min Act: -0.0000

Data Index: 308780 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 9.8202. Min Range: -9.8202

Max Act: 8.9278. Min Act: -0.0000

Data Index: 1339985 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.7766. Min Act: -0.0000

Data Index: 688040 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 9.8202. Min Range: -9.8202

Max Act: 8.1772. Min Act: -0.0000

Data Index: 418971 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.5135. Min Act: -0.0000

Data Index: 1143340 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.1838. Min Act: -0.0000

Data Index: 493388 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.8568. Min Act: -0.0000

Data Index: 134640 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.1965. Min Act: -0.0000

Data Index: 959389 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.7437. Min Act: -0.0000

Data Index: 1143628 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.0296. Min Act: -0.0000

Data Index: 713590 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.7389. Min Act: -0.0000

Data Index: 870353 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.0398. Min Act: -0.0000

Data Index: 77367 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.2546. Min Act: -0.0000

Data Index: 182095 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 9.8202. Min Range: -9.8202

Max Act: 7.1802. Min Act: -0.0000

Data Index: 1342674 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.1774. Min Act: -0.0000

Data Index: 711358 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 9.8202. Min Range: -9.8202

Max Act: 5.9251. Min Act: -0.0000

Data Index: 1070615 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.2304. Min Act: -0.0000

Data Index: 355874 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.3830. Min Act: -0.0000

Data Index: 152930 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.3688. Min Act: -0.0000

Data Index: 176283 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 9.8202. Min Range: -9.8202

Max Act: 6.3183. Min Act: -0.0000

Data Index: 1021589 (C4 (Web Text))

Max Activating Token Index: 48