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

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

Neuron 1890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1296055 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6984. Min Act: -0.0000

Data Index: 502372 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1131286 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1019472 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5309. Min Act: -0.0000

Data Index: 788268 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6565. Min Act: -0.0000

Data Index: 491113 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5760. Min Act: -0.0000

Data Index: 836987 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5958. Min Act: -0.0000

Data Index: 638722 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1461797 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5824. Min Act: -0.0000

Data Index: 209404 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5577. Min Act: -0.0000

Data Index: 890015 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5557. Min Act: -0.0000

Data Index: 676813 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5512. Min Act: -0.0000

Data Index: 700291 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5846. Min Act: -0.0000

Data Index: 30077 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5445. Min Act: -0.0000

Data Index: 331189 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5677. Min Act: -0.0000

Data Index: 654298 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5396. Min Act: -0.0000

Data Index: 729621 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5456. Min Act: -0.0000

Data Index: 358302 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1040149 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5193. Min Act: -0.0000

Data Index: 635336 (C4 (Web Text))

Max Activating Token Index: 512