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

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

Neuron 6007 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.6235. Min Act: -0.0000

Data Index: 1406789 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.2787. Min Act: -0.0000

Data Index: 1575151 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.4196. Min Act: -0.0000

Data Index: 1392237 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.1860. Min Act: -0.0000

Data Index: 1484878 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.3218. Min Act: -0.0000

Data Index: 1388988 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.9812. Min Act: -0.0000

Data Index: 1413008 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.2823. Min Act: -0.0000

Data Index: 1410277 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.2655. Min Act: -0.0000

Data Index: 1420996 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.0647. Min Act: -0.0000

Data Index: 1586178 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.9054. Min Act: -0.0000

Data Index: 1414006 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.9944. Min Act: -0.0000

Data Index: 1536603 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.1545. Min Act: -0.0000

Data Index: 1549698 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.8517. Min Act: -0.0000

Data Index: 1359890 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.2786. Min Act: -0.0000

Data Index: 1530120 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.9656. Min Act: -0.0000

Data Index: 1414321 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.9501. Min Act: -0.0000

Data Index: 1507606 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 4.6235. Min Range: -4.6235

Max Act: 4.0931. Min Act: -0.0000

Data Index: 1652332 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.7747. Min Act: -0.0000

Data Index: 1576649 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.7654. Min Act: -0.0000

Data Index: 1435708 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 4.6235. Min Range: -4.6235

Max Act: 3.8104. Min Act: -0.0000

Data Index: 1466299 (Python Code)

Max Activating Token Index: 138