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

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

Neuron 305 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: 0.0547. Min Range: -0.0547

Max Act: 0.0546. Min Act: -0.0005

Data Index: 92900 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0541. Min Act: -0.0005

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0005

Data Index: 65250 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0531. Min Act: -0.0005

Data Index: 445129 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0511. Min Act: -0.0005

Data Index: 915178 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0509. Min Act: -0.0005

Data Index: 783101 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0517. Min Act: -0.0005

Data Index: 922591 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0511. Min Act: -0.0004

Data Index: 860615 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0511. Min Act: -0.0005

Data Index: 1232278 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0496. Min Act: -0.0005

Data Index: 867951 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0491. Min Act: -0.0005

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0501. Min Act: -0.0005

Data Index: 984062 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0480. Min Act: -0.0005

Data Index: 1052215 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0474. Min Act: -0.0005

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0483. Min Act: -0.0005

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0473. Min Act: -0.0004

Data Index: 1161473 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0460. Min Act: -0.0005

Data Index: 258316 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0466. Min Act: -0.0005

Data Index: 961317 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1061258 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0469. Min Act: -0.0005

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 620