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

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

Neuron 3991 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1778. Min Act: -0.0002

Data Index: 1067270 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1561. Min Act: -0.0001

Data Index: 417935 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1558. Min Act: -0.0001

Data Index: 58636 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1511. Min Act: -0.0001

Data Index: 295646 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1124244 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1436. Min Act: -0.0001

Data Index: 399075 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1428. Min Act: -0.0001

Data Index: 277626 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1375. Min Act: -0.0001

Data Index: 4286 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1383. Min Act: -0.0001

Data Index: 749073 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1351. Min Act: -0.0001

Data Index: 234847 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1315. Min Act: -0.0001

Data Index: 52870 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1322. Min Act: -0.0001

Data Index: 977819 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1312. Min Act: -0.0001

Data Index: 92271 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1277. Min Act: -0.0001

Data Index: 864861 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1247. Min Act: -0.0001

Data Index: 383640 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1295. Min Act: -0.0001

Data Index: 793221 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1248. Min Act: -0.0001

Data Index: 899129 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1241. Min Act: -0.0001

Data Index: 708159 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1277. Min Act: -0.0002

Data Index: 924282 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.1778. Min Range: -0.1778

Max Act: 0.1250. Min Act: -0.0001

Data Index: 679150 (C4 (Web Text))

Max Activating Token Index: 987