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

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

Neuron 5464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1383427 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1374921 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1361307 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1430758 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1622057 (Python Code)

Max Activating Token Index: 201

Text #5

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1530950 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1431232 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1645871 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1473141 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1461043 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1402959 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1449834 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1628816 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1377488 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1439216 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1396981 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1608559 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 1.3902. Min Range: -1.3902

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1492237 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 1.3902. Min Range: -1.3902

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1506907 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 1.3902. Min Range: -1.3902

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1466164 (Python Code)

Max Activating Token Index: 715