Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0001

Data Index: 128376 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0503. Min Act: -0.0001

Data Index: 667975 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0521. Min Act: -0.0001

Data Index: 546571 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0514. Min Act: -0.0001

Data Index: 686370 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0482. Min Act: -0.0001

Data Index: 18355 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1277366 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0455. Min Act: -0.0001

Data Index: 594277 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0476. Min Act: -0.0001

Data Index: 880120 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0507. Min Act: -0.0001

Data Index: 200706 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1335784 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0481. Min Act: -0.0001

Data Index: 725239 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0454. Min Act: -0.0001

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0456. Min Act: -0.0001

Data Index: 375976 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1150554 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1022540 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0425. Min Act: -0.0001

Data Index: 56248 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0456. Min Act: -0.0001

Data Index: 58476 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0442. Min Act: -0.0001

Data Index: 871480 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0449. Min Act: -0.0001

Data Index: 841665 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0456. Min Act: -0.0001

Data Index: 222888 (C4 (Web Text))

Max Activating Token Index: 748