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

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

Neuron 523 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1235. Min Range: -2.1235

Max Act: 2.1235. Min Act: -0.0000

Data Index: 55532 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.9722. Min Act: -0.0000

Data Index: 703374 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.9661. Min Act: -0.0000

Data Index: 775954 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.8120. Min Act: -0.0000

Data Index: 209495 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.9047. Min Act: -0.0000

Data Index: 877960 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7985. Min Act: -0.0000

Data Index: 994283 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7957. Min Act: -0.0000

Data Index: 361438 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7692. Min Act: 0.0000

Data Index: 1192570 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1384925 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7266. Min Act: -0.0000

Data Index: 309301 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6969. Min Act: -0.0000

Data Index: 213150 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6945. Min Act: -0.0000

Data Index: 441283 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.7661. Min Act: -0.0000

Data Index: 924867 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6609. Min Act: -0.0000

Data Index: 142179 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1259656 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.5615. Min Act: 0.0000

Data Index: 687398 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1305662 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1323754 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.6143. Min Act: -0.0000

Data Index: 94660 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 2.1235. Min Range: -2.1235

Max Act: 1.5125. Min Act: -0.0000

Data Index: 926885 (C4 (Web Text))

Max Activating Token Index: 179