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

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

Neuron 1466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0001

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1345. Min Act: -0.0001

Data Index: 602192 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1438877 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1408377 (Python Code)

Max Activating Token Index: 245

Text #4

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1625130 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1136769 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1422934 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1534339 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1259. Min Act: -0.0001

Data Index: 1360483 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1257. Min Act: -0.0001

Data Index: 540923 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1386. Min Act: -0.0001

Data Index: 686718 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1624148 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1112. Min Act: -0.0001

Data Index: 544750 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1399608 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1500839 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1199. Min Act: -0.0001

Data Index: 547952 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1575322 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1427938 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1568199 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1587185 (Python Code)

Max Activating Token Index: 366