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

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

Neuron 5425 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: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1338275 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1482515 (Python Code)

Max Activating Token Index: 779

Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1611155 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1452967 (Python Code)

Max Activating Token Index: 414

Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1656913 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1562379 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1406008 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1377477 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1510715 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1466381 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1529889 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1482819 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1648579 (Python Code)

Max Activating Token Index: 859

Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1368477 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1611172 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1542160 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1430769 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1406705 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1502769 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2867. Min Act: -0.0000

Data Index: 389091 (C4 (Web Text))

Max Activating Token Index: 46