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

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

Neuron 5316 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0001

Data Index: 881335 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1412. Min Act: -0.0001

Data Index: 424918 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1536. Min Act: -0.0001

Data Index: 849977 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1467. Min Act: -0.0001

Data Index: 758583 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1412. Min Act: -0.0001

Data Index: 115577 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1441. Min Act: -0.0001

Data Index: 846325 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1352. Min Act: -0.0001

Data Index: 131996 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1376. Min Act: -0.0002

Data Index: 751654 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1411. Min Act: -0.0001

Data Index: 874120 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1290635 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1188083 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1362. Min Act: -0.0001

Data Index: 836305 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1293930 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1263. Min Act: -0.0001

Data Index: 238935 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1402. Min Act: -0.0001

Data Index: 40850 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1408. Min Act: -0.0001

Data Index: 632947 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1285. Min Act: -0.0001

Data Index: 15390 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1274292 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1242800 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1099661 (C4 (Web Text))

Max Activating Token Index: 668