Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2685 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9472. Min Act: -0.0001

Data Index: 91369 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.9894. Min Act: -0.0001

Data Index: 958155 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.6040. Min Act: -0.0001

Data Index: 1355467 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.7451. Min Act: -0.0001

Data Index: 1046253 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.8367. Min Act: -0.0001

Data Index: 1247537 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.6812. Min Act: -0.0001

Data Index: 1213597 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.6736. Min Act: -0.0001

Data Index: 932471 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4994. Min Act: -0.0001

Data Index: 291480 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.7286. Min Act: -0.0001

Data Index: 1250555 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.5650. Min Act: -0.0001

Data Index: 177109 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4368. Min Act: -0.0001

Data Index: 1005086 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4219. Min Act: -0.0001

Data Index: 576150 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.3983. Min Act: -0.0001

Data Index: 770386 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4754. Min Act: -0.0001

Data Index: 825128 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.3788. Min Act: -0.0001

Data Index: 1118682 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4552. Min Act: -0.0001

Data Index: 1014009 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.5383. Min Act: -0.0001

Data Index: 932233 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.4490. Min Act: -0.0001

Data Index: 434365 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.2955. Min Act: -0.0001

Data Index: 213711 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.9894. Min Range: -1.9894

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1245000 (C4 (Web Text))

Max Activating Token Index: 324