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

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

Neuron 3031 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: 1.0821. Min Range: -1.0821

Max Act: 1.0821. Min Act: -0.0002

Data Index: 1300384 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0567. Min Act: -0.0002

Data Index: 102869 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0086. Min Act: -0.0002

Data Index: 779922 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0125. Min Act: -0.0002

Data Index: 1015511 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0022. Min Act: -0.0002

Data Index: 784786 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9988. Min Act: -0.0002

Data Index: 784002 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.0821. Min Range: -1.0821

Max Act: 1.0180. Min Act: -0.0002

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9922. Min Act: -0.0002

Data Index: 942283 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9931. Min Act: -0.0002

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9779. Min Act: -0.0002

Data Index: 631704 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9571. Min Act: -0.0002

Data Index: 166437 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9411. Min Act: -0.0002

Data Index: 118809 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9391. Min Act: -0.0002

Data Index: 973123 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9339. Min Act: -0.0002

Data Index: 1094131 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9234. Min Act: -0.0002

Data Index: 702799 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9396. Min Act: -0.0002

Data Index: 648388 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9193. Min Act: -0.0002

Data Index: 285719 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9360. Min Act: -0.0002

Data Index: 496532 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9277. Min Act: -0.0002

Data Index: 182860 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.0821. Min Range: -1.0821

Max Act: 0.9348. Min Act: -0.0002

Data Index: 203816 (C4 (Web Text))

Max Activating Token Index: 669