Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1157770 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1574. Min Act: -0.0001

Data Index: 82755 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1629. Min Act: -0.0001

Data Index: 887307 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1172709 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1531. Min Act: -0.0001

Data Index: 140452 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1460. Min Act: -0.0001

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1473. Min Act: -0.0001

Data Index: 729542 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1438. Min Act: -0.0001

Data Index: 115020 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1396. Min Act: -0.0001

Data Index: 524959 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1416. Min Act: -0.0001

Data Index: 30472 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1299. Min Act: -0.0001

Data Index: 204091 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1205. Min Act: -0.0001

Data Index: 69804 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1316. Min Act: -0.0001

Data Index: 780914 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1241405 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1210. Min Act: -0.0000

Data Index: 204841 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1219503 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1336. Min Act: -0.0001

Data Index: 610669 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1318781 (C4 (Web Text))

Max Activating Token Index: 945