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

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

Neuron 3143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 966140 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1057738 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0537. Min Act: -0.0002

Data Index: 481455 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1006325 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0507. Min Act: -0.0002

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0518. Min Act: -0.0002

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0525. Min Act: -0.0002

Data Index: 675481 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0502. Min Act: -0.0002

Data Index: 892383 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0466. Min Act: -0.0002

Data Index: 979650 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0453. Min Act: -0.0002

Data Index: 119801 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0531. Min Act: -0.0002

Data Index: 333496 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0412. Min Act: -0.0002

Data Index: 899633 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0459. Min Act: -0.0002

Data Index: 949619 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0435. Min Act: -0.0002

Data Index: 369336 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0475. Min Act: -0.0002

Data Index: 759843 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0423. Min Act: -0.0002

Data Index: 861266 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0414. Min Act: -0.0002

Data Index: 615503 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0467. Min Act: -0.0002

Data Index: 489349 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0425. Min Act: -0.0002

Data Index: 441531 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1567287 (Python Code)

Max Activating Token Index: 676