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

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

Neuron 3234 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: 0.9248. Min Range: -0.9248

Max Act: 0.9248. Min Act: -0.0002

Data Index: 1316817 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8959. Min Act: -0.0002

Data Index: 558945 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8905. Min Act: -0.0002

Data Index: 272580 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8814. Min Act: -0.0002

Data Index: 55168 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9139. Min Act: -0.0002

Data Index: 344891 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8958. Min Act: -0.0002

Data Index: 68039 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8450. Min Act: -0.0002

Data Index: 1056103 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8807. Min Act: -0.0002

Data Index: 660908 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8552. Min Act: -0.0002

Data Index: 1105209 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8589. Min Act: -0.0002

Data Index: 307044 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8464. Min Act: -0.0002

Data Index: 41323 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8298. Min Act: -0.0002

Data Index: 1022019 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8214. Min Act: -0.0002

Data Index: 90567 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8324. Min Act: -0.0002

Data Index: 1082795 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8518. Min Act: -0.0002

Data Index: 905659 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8310. Min Act: -0.0002

Data Index: 487811 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8565. Min Act: -0.0002

Data Index: 1098839 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7908. Min Act: -0.0002

Data Index: 1327139 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8237. Min Act: -0.0002

Data Index: 291989 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8310. Min Act: -0.0002

Data Index: 1258914 (C4 (Web Text))

Max Activating Token Index: 700