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

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

Neuron 311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1623492 (Python Code)

Max Activating Token Index: 290

Text #1

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1650923 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1623975 (Python Code)

Max Activating Token Index: 192

Text #3

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1409814 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1526153 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1587062 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1542708 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1383819 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1371. Min Act: -0.0001

Data Index: 165781 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1422459 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1626786 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1267. Min Act: -0.0001

Data Index: 614939 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1578158 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1536764 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1505690 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1434705 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1527608 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1581457 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1475985 (Python Code)

Max Activating Token Index: 775