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

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

Neuron 3011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6372. Min Range: -3.6372

Max Act: 3.6372. Min Act: -0.0000

Data Index: 824139 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.8234. Min Act: -0.0000

Data Index: 37187 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.7906. Min Act: -0.0000

Data Index: 812118 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.6467. Min Act: -0.0000

Data Index: 762203 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.5789. Min Act: -0.0000

Data Index: 993580 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.5967. Min Act: -0.0000

Data Index: 1213695 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.5225. Min Act: -0.0000

Data Index: 479594 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.3704. Min Act: -0.0000

Data Index: 607933 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.3765. Min Act: -0.0000

Data Index: 343200 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.6296. Min Act: -0.0000

Data Index: 707485 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.3350. Min Act: -0.0000

Data Index: 536179 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2025. Min Act: -0.0000

Data Index: 519263 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1126028 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.5531. Min Act: -0.0000

Data Index: 800099 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2605. Min Act: -0.0000

Data Index: 657492 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2643. Min Act: -0.0000

Data Index: 959995 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2531. Min Act: -0.0000

Data Index: 1163935 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2514. Min Act: -0.0000

Data Index: 888583 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.2310. Min Act: -0.0000

Data Index: 480201 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 3.6372. Min Range: -3.6372

Max Act: 2.1175. Min Act: -0.0000

Data Index: 1307899 (C4 (Web Text))

Max Activating Token Index: 261