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

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

Neuron 4640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.7843. Min Act: -0.0001

Data Index: 1556244 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5858. Min Act: -0.0001

Data Index: 1569243 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5899. Min Act: -0.0001

Data Index: 1520097 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5849. Min Act: -0.0001

Data Index: 1404663 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.7241. Min Act: -0.0001

Data Index: 1547055 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5370. Min Act: -0.0001

Data Index: 1483120 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5318. Min Act: -0.0001

Data Index: 1626009 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5159. Min Act: -0.0001

Data Index: 1424925 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5162. Min Act: -0.0001

Data Index: 1496512 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.7878. Min Act: -0.0001

Data Index: 1378839 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4399. Min Act: -0.0001

Data Index: 1395176 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.6060. Min Act: -0.0001

Data Index: 1648097 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4347. Min Act: -0.0001

Data Index: 1455387 (Python Code)

Max Activating Token Index: 913

Text #13

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4485. Min Act: -0.0001

Data Index: 1647047 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5865. Min Act: -0.0001

Data Index: 1478939 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5853. Min Act: -0.0001

Data Index: 1391414 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.5859. Min Act: -0.0001

Data Index: 1484561 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4290. Min Act: -0.0001

Data Index: 1570136 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4118. Min Act: -0.0001

Data Index: 1376129 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 3.7878. Min Range: -3.7878

Max Act: 3.4178. Min Act: -0.0001

Data Index: 1499015 (Python Code)

Max Activating Token Index: 122