Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2079 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0001

Data Index: 749538 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0430. Min Act: -0.0001

Data Index: 569308 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0377. Min Act: -0.0001

Data Index: 71856 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0392. Min Act: -0.0001

Data Index: 28893 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0402. Min Act: -0.0001

Data Index: 72763 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0386. Min Act: -0.0001

Data Index: 398415 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1562384 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1050342 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0356. Min Act: -0.0001

Data Index: 80548 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0379. Min Act: -0.0001

Data Index: 951758 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1010754 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0391. Min Act: -0.0001

Data Index: 787783 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1040514 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0401. Min Act: -0.0001

Data Index: 628502 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1118108 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1457913 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0353. Min Act: -0.0001

Data Index: 304094 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0365. Min Act: -0.0001

Data Index: 634759 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0365. Min Act: -0.0001

Data Index: 230009 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0351. Min Act: -0.0001

Data Index: 759164 (C4 (Web Text))

Max Activating Token Index: 451