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

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

Neuron 226 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: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1057520 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1864. Min Act: -0.0000

Data Index: 277962 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1618706 (Python Code)

Max Activating Token Index: 307

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1186939 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1535048 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1651. Min Act: -0.0000

Data Index: 979815 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1000560 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1445734 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1050372 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1442. Min Act: -0.0000

Data Index: 514336 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1316. Min Act: -0.0000

Data Index: 397692 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1228280 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1349. Min Act: -0.0000

Data Index: 620126 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1337. Min Act: -0.0000

Data Index: 397688 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1373435 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1293. Min Act: -0.0000

Data Index: 331410 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1240. Min Act: -0.0000

Data Index: 253767 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1274. Min Act: -0.0000

Data Index: 615649 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1227. Min Act: -0.0000

Data Index: 284774 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1324. Min Act: -0.0000

Data Index: 435153 (C4 (Web Text))

Max Activating Token Index: 346