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

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

Neuron 1754 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: 0.1491. Min Range: -0.1491

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1588239 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1379. Min Act: -0.0000

Data Index: 125922 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1588543 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1208. Min Act: -0.0000

Data Index: 873887 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1191. Min Act: -0.0000

Data Index: 61540 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1161587 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1412509 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1350633 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1257448 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0949. Min Act: -0.0000

Data Index: 645676 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1002172 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1122273 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1191450 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1508948 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1122704 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0894. Min Act: -0.0000

Data Index: 575348 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1167127 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0861. Min Act: -0.0000

Data Index: 507606 (C4 (Web Text))

Max Activating Token Index: 926