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

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

Neuron 904 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0002

Data Index: 849570 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1035263 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0531. Min Act: -0.0002

Data Index: 45576 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0475. Min Act: -0.0002

Data Index: 607388 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1201575 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0514. Min Act: -0.0002

Data Index: 849404 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0506. Min Act: -0.0002

Data Index: 201451 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1264576 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0480. Min Act: -0.0002

Data Index: 193210 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0482. Min Act: -0.0002

Data Index: 142432 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0474. Min Act: -0.0002

Data Index: 481186 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0453. Min Act: -0.0001

Data Index: 564914 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0464. Min Act: -0.0002

Data Index: 774387 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0457. Min Act: -0.0002

Data Index: 349525 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0447. Min Act: -0.0002

Data Index: 528959 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0448. Min Act: -0.0002

Data Index: 443543 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1247949 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0452. Min Act: -0.0002

Data Index: 730544 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0451. Min Act: -0.0002

Data Index: 330840 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0469. Min Act: -0.0002

Data Index: 451641 (C4 (Web Text))

Max Activating Token Index: 108