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

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

Neuron 220 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.7858. Min Act: -0.0000

Data Index: 1443116 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.7682. Min Act: 0.0000

Data Index: 1389378 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.5530. Min Act: -0.0000

Data Index: 1422191 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.5775. Min Act: -0.0000

Data Index: 1375948 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.4562. Min Act: -0.0000

Data Index: 1533207 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.5268. Min Act: -0.0000

Data Index: 1383792 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.5060. Min Act: 0.0000

Data Index: 1428661 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.6180. Min Act: 0.0000

Data Index: 1398966 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.4323. Min Act: 0.0000

Data Index: 1614052 (Python Code)

Max Activating Token Index: 778

Text #9

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2117. Min Act: -0.0000

Data Index: 1555488 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.3172. Min Act: -0.0000

Data Index: 1373640 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2954. Min Act: 0.0000

Data Index: 1590075 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2905. Min Act: 0.0000

Data Index: 1454337 (Python Code)

Max Activating Token Index: 335

Text #13

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2303. Min Act: 0.0000

Data Index: 1637868 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2062. Min Act: 0.0000

Data Index: 1525628 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1523970 (Python Code)

Max Activating Token Index: 702

Text #16

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1587405 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.1556. Min Act: 0.0000

Data Index: 1596479 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.1281. Min Act: 0.0000

Data Index: 1534122 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.1585. Min Act: 0.0000

Data Index: 1490895 (Python Code)

Max Activating Token Index: 941