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

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

Neuron 1979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0521. Min Act: -0.0001

Data Index: 739342 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1153076 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0501. Min Act: -0.0001

Data Index: 841544 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0464. Min Act: -0.0002

Data Index: 72827 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0434. Min Act: -0.0001

Data Index: 20198 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1046717 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0449. Min Act: -0.0002

Data Index: 401430 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0445. Min Act: -0.0002

Data Index: 586292 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0445. Min Act: -0.0002

Data Index: 25834 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0428. Min Act: -0.0001

Data Index: 571796 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0453. Min Act: -0.0001

Data Index: 82392 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0456. Min Act: -0.0001

Data Index: 425808 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1257063 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0432. Min Act: -0.0002

Data Index: 677621 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0416. Min Act: -0.0002

Data Index: 421344 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0417. Min Act: -0.0001

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0421. Min Act: -0.0001

Data Index: 454470 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0427. Min Act: -0.0002

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0428. Min Act: -0.0001

Data Index: 414058 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1206600 (C4 (Web Text))

Max Activating Token Index: 6