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

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

Neuron 2817 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5216. Min Range: -4.5216

Max Act: 4.5216. Min Act: -0.0000

Data Index: 1404121 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 4.5216. Min Range: -4.5216

Max Act: 4.4388. Min Act: -0.0000

Data Index: 1363431 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 4.5216. Min Range: -4.5216

Max Act: 4.3929. Min Act: -0.0000

Data Index: 1528914 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 4.5216. Min Range: -4.5216

Max Act: 4.3070. Min Act: -0.0000

Data Index: 1397749 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.9404. Min Act: -0.0000

Data Index: 1406217 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 4.5216. Min Range: -4.5216

Max Act: 4.0981. Min Act: -0.0000

Data Index: 1628219 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.7970. Min Act: -0.0000

Data Index: 1492153 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.8932. Min Act: -0.0000

Data Index: 1573138 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.5930. Min Act: -0.0000

Data Index: 1596171 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.5787. Min Act: -0.0000

Data Index: 1463152 (Python Code)

Max Activating Token Index: 210

Text #10

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.6449. Min Act: -0.0000

Data Index: 1411315 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.4798. Min Act: -0.0000

Data Index: 1597186 (Python Code)

Max Activating Token Index: 419

Text #12

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.4683. Min Act: -0.0000

Data Index: 1560253 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1635919 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.5985. Min Act: -0.0000

Data Index: 1406816 (Python Code)

Max Activating Token Index: 231

Text #15

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.4043. Min Act: -0.0000

Data Index: 1514449 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.2394. Min Act: -0.0000

Data Index: 1523248 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.2145. Min Act: -0.0000

Data Index: 1410211 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.2831. Min Act: -0.0000

Data Index: 1597006 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 4.5216. Min Range: -4.5216

Max Act: 3.2582. Min Act: -0.0000

Data Index: 1478855 (Python Code)

Max Activating Token Index: 401