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

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

Neuron 2555 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: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1581414 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1565524 (Python Code)

Max Activating Token Index: 787

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3779. Min Act: -0.0000

Data Index: 645411 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3785. Min Act: -0.0000

Data Index: 863751 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1632626 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1440172 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3494. Min Act: -0.0000

Data Index: 628548 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1451357 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1498648 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1475498 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1365584 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1538944 (Python Code)

Max Activating Token Index: 806

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1624167 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1535835 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3115. Min Act: -0.0000

Data Index: 304632 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3140. Min Act: -0.0000

Data Index: 752343 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1472861 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3036. Min Act: -0.0000

Data Index: 310944 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1412666 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1496511 (Python Code)

Max Activating Token Index: 613