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

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

Neuron 1013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1080. Min Range: -1.1080

Max Act: 1.1080. Min Act: -0.0000

Data Index: 361247 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1455714 (Python Code)

Max Activating Token Index: 521

Text #2

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8926. Min Act: -0.0000

Data Index: 923003 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1436304 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1435158 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1460182 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7298. Min Act: -0.0000

Data Index: 78876 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1304150 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1333317 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7067. Min Act: -0.0000

Data Index: 481119 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6818. Min Act: -0.0000

Data Index: 995653 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7138. Min Act: -0.0000

Data Index: 149295 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6465. Min Act: -0.0000

Data Index: 879152 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1549653 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1339546 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6440. Min Act: -0.0000

Data Index: 600908 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6206. Min Act: -0.0000

Data Index: 851765 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1411895 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1467547 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.5933. Min Act: -0.0000

Data Index: 754756 (C4 (Web Text))

Max Activating Token Index: 560