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

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

Neuron 4820 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: 3.5930. Min Range: -3.5930

Max Act: 3.5930. Min Act: -0.0000

Data Index: 1432974 (Python Code)

Max Activating Token Index: 763

Text #1

Max Range: 3.5930. Min Range: -3.5930

Max Act: 3.1835. Min Act: -0.0000

Data Index: 1505451 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.7005. Min Act: -0.0000

Data Index: 1517122 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.6791. Min Act: -0.0000

Data Index: 1515075 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.8275. Min Act: -0.0000

Data Index: 1361649 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.6344. Min Act: -0.0000

Data Index: 1623338 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.5720. Min Act: -0.0000

Data Index: 1540558 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.6524. Min Act: -0.0000

Data Index: 1257134 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.3641. Min Act: -0.0000

Data Index: 1549141 (Python Code)

Max Activating Token Index: 1007

Text #9

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.4749. Min Act: -0.0000

Data Index: 1569116 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1209196 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.2814. Min Act: -0.0000

Data Index: 1086795 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.2348. Min Act: -0.0000

Data Index: 1497063 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.2129. Min Act: -0.0000

Data Index: 1084530 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.5930. Min Range: -3.5930

Max Act: 1.8745. Min Act: -0.0000

Data Index: 519217 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.2089. Min Act: -0.0000

Data Index: 435389 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.2728. Min Act: -0.0000

Data Index: 486285 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.5930. Min Range: -3.5930

Max Act: 1.9795. Min Act: -0.0000

Data Index: 1430247 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.1728. Min Act: -0.0000

Data Index: 1056332 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.5930. Min Range: -3.5930

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1593795 (Python Code)

Max Activating Token Index: 639