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

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

Neuron 15 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: 3.0963. Min Range: -3.0963

Max Act: 3.0963. Min Act: -0.0000

Data Index: 1431626 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.9531. Min Act: -0.0000

Data Index: 1575589 (Python Code)

Max Activating Token Index: 663

Text #2

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.6918. Min Act: -0.0000

Data Index: 1449571 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1554057 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.5450. Min Act: -0.0000

Data Index: 1608220 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.6805. Min Act: -0.0000

Data Index: 1649777 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.5207. Min Act: -0.0000

Data Index: 1639274 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1411670 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1473162 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.2145. Min Act: -0.0000

Data Index: 387158 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.5580. Min Act: -0.0000

Data Index: 1585077 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.4066. Min Act: -0.0000

Data Index: 1477613 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.4553. Min Act: -0.0000

Data Index: 1638429 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.3873. Min Act: -0.0000

Data Index: 1590114 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1393996 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1539187 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 3.0963. Min Range: -3.0963

Max Act: 1.9126. Min Act: -0.0000

Data Index: 1550920 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1586223 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 3.0963. Min Range: -3.0963

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1458655 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 3.0963. Min Range: -3.0963

Max Act: 1.9065. Min Act: -0.0000

Data Index: 489777 (C4 (Web Text))

Max Activating Token Index: 268