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

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

Neuron 1120 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: 0.1783. Min Range: -0.1783

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1244666 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1674. Min Act: -0.0000

Data Index: 468587 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1510. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1520. Min Act: -0.0001

Data Index: 451033 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1399. Min Act: -0.0001

Data Index: 468359 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1090950 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1492565 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1285768 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1279. Min Act: -0.0001

Data Index: 3729 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1259. Min Act: -0.0001

Data Index: 541064 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1321072 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1285. Min Act: -0.0000

Data Index: 426462 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1257. Min Act: -0.0001

Data Index: 873015 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1259. Min Act: -0.0000

Data Index: 129517 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1284. Min Act: -0.0001

Data Index: 283967 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1520373 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1403286 (Python Code)

Max Activating Token Index: 109

Text #19

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1031597 (C4 (Web Text))

Max Activating Token Index: 650