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

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

Neuron 569 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: 0.4346. Min Range: -0.4346

Max Act: 0.4346. Min Act: -0.0002

Data Index: 1636726 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4070. Min Act: -0.0002

Data Index: 1397632 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4087. Min Act: -0.0002

Data Index: 1369986 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4141. Min Act: -0.0002

Data Index: 1554093 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4004. Min Act: -0.0002

Data Index: 1559417 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4088. Min Act: -0.0002

Data Index: 1557329 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3920. Min Act: -0.0002

Data Index: 1553889 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3922. Min Act: -0.0002

Data Index: 1518882 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4006. Min Act: -0.0002

Data Index: 1431140 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3925. Min Act: -0.0002

Data Index: 1514165 (Python Code)

Max Activating Token Index: 432

Text #10

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3888. Min Act: -0.0002

Data Index: 1466306 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3878. Min Act: -0.0002

Data Index: 1615151 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3874. Min Act: -0.0002

Data Index: 1491852 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3921. Min Act: -0.0002

Data Index: 1390766 (Python Code)

Max Activating Token Index: 705

Text #14

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3924. Min Act: -0.0002

Data Index: 1642703 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3793. Min Act: -0.0002

Data Index: 1436006 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3840. Min Act: -0.0002

Data Index: 1470485 (Python Code)

Max Activating Token Index: 661

Text #17

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3795. Min Act: -0.0002

Data Index: 1541373 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3750. Min Act: -0.0002

Data Index: 1517514 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3775. Min Act: -0.0002

Data Index: 1457047 (Python Code)

Max Activating Token Index: 169