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

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

Neuron 2342 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: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1216907 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1054306 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1607. Min Act: -0.0001

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1316206 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1375. Min Act: -0.0001

Data Index: 10360 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1325. Min Act: -0.0001

Data Index: 146325 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1259099 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1292. Min Act: -0.0001

Data Index: 545595 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1342. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1249555 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1309. Min Act: -0.0001

Data Index: 493919 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1259. Min Act: -0.0001

Data Index: 254064 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1225. Min Act: -0.0001

Data Index: 492539 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1265. Min Act: -0.0001

Data Index: 622117 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1326374 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1261. Min Act: -0.0001

Data Index: 4187 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1254. Min Act: -0.0001

Data Index: 238083 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1198543 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1249. Min Act: -0.0001

Data Index: 246346 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1293. Min Act: -0.0001

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 604