Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 422 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2472. Min Act: -0.0002

Data Index: 1523153 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2440. Min Act: -0.0002

Data Index: 1396926 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2298. Min Act: -0.0002

Data Index: 1515129 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2016. Min Act: -0.0002

Data Index: 1428273 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2288. Min Act: -0.0002

Data Index: 1552908 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2285. Min Act: -0.0002

Data Index: 1398313 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2108. Min Act: -0.0002

Data Index: 1536576 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2072. Min Act: -0.0002

Data Index: 1579952 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2197. Min Act: -0.0002

Data Index: 1413439 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2091. Min Act: -0.0002

Data Index: 1410540 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2002. Min Act: -0.0002

Data Index: 1370206 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2194. Min Act: -0.0002

Data Index: 1611116 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2145. Min Act: -0.0002

Data Index: 1482839 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2034. Min Act: -0.0002

Data Index: 1426958 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2065. Min Act: -0.0002

Data Index: 1571665 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2108. Min Act: -0.0002

Data Index: 1418501 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1397240 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2140. Min Act: -0.0002

Data Index: 1490264 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2087. Min Act: -0.0002

Data Index: 1545906 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.1861. Min Act: -0.0002

Data Index: 1578566 (Python Code)

Max Activating Token Index: 282