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

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

Neuron 327 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: 0.1107. Min Range: -0.1107

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1554142 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1391394 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1619383 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1435115 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1406983 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1376529 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1652652 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1390127 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1197718 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1586377 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1422842 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1374081 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1426207 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1584151 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1649722 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1434195 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0817. Min Act: -0.0002

Data Index: 946061 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1461960 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0824. Min Act: -0.0002

Data Index: 911466 (C4 (Web Text))

Max Activating Token Index: 185