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

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

Neuron 3407 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.6291. Min Act: -0.0002

Data Index: 1634942 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.6122. Min Act: -0.0002

Data Index: 1611094 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.4937. Min Act: -0.0002

Data Index: 1581901 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.5006. Min Act: -0.0002

Data Index: 1612916 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.4546. Min Act: -0.0002

Data Index: 1488784 (Python Code)

Max Activating Token Index: 504

Text #5

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3954. Min Act: -0.0002

Data Index: 1435035 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3936. Min Act: -0.0002

Data Index: 1523117 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3730. Min Act: -0.0002

Data Index: 1468702 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3812. Min Act: -0.0002

Data Index: 1466201 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3696. Min Act: -0.0002

Data Index: 1416132 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3255. Min Act: -0.0002

Data Index: 1612886 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3240. Min Act: -0.0002

Data Index: 1519888 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3333. Min Act: -0.0002

Data Index: 1473899 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3168. Min Act: -0.0002

Data Index: 1497462 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3271. Min Act: -0.0002

Data Index: 1552088 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3168. Min Act: -0.0002

Data Index: 1522766 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.2933. Min Act: -0.0002

Data Index: 1467454 (Python Code)

Max Activating Token Index: 530

Text #17

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.2950. Min Act: -0.0002

Data Index: 1466960 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.2996. Min Act: -0.0002

Data Index: 1656549 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3194. Min Act: -0.0002

Data Index: 1550337 (Python Code)

Max Activating Token Index: 360