Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0005

Data Index: 541428 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0455. Min Act: -0.0005

Data Index: 546062 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0467. Min Act: -0.0005

Data Index: 1093022 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0444. Min Act: -0.0005

Data Index: 580479 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1003811 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0431. Min Act: -0.0005

Data Index: 59591 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0445. Min Act: -0.0005

Data Index: 426096 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1222829 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0424. Min Act: -0.0005

Data Index: 227298 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1074840 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1324726 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0388. Min Act: -0.0005

Data Index: 638631 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0366. Min Act: -0.0005

Data Index: 83265 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0393. Min Act: -0.0005

Data Index: 197154 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0342. Min Act: -0.0005

Data Index: 586250 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0364. Min Act: -0.0005

Data Index: 64198 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1229955 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0359. Min Act: -0.0005

Data Index: 187266 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0356. Min Act: -0.0005

Data Index: 1291251 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0355. Min Act: -0.0005

Data Index: 428586 (C4 (Web Text))

Max Activating Token Index: 235