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

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

Neuron 4081 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0001

Data Index: 575148 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0548. Min Act: -0.0001

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0519. Min Act: -0.0000

Data Index: 218547 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0468. Min Act: -0.0001

Data Index: 94559 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1019067 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0481. Min Act: -0.0001

Data Index: 170355 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0464. Min Act: -0.0000

Data Index: 232939 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1535706 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0496. Min Act: -0.0001

Data Index: 971112 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0465. Min Act: -0.0001

Data Index: 848420 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0460. Min Act: -0.0001

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0474. Min Act: -0.0001

Data Index: 589769 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0427. Min Act: -0.0001

Data Index: 433667 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0423. Min Act: -0.0001

Data Index: 335309 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0416. Min Act: -0.0001

Data Index: 168740 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0444. Min Act: -0.0000

Data Index: 964679 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0411. Min Act: -0.0000

Data Index: 381747 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0406. Min Act: -0.0001

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0425. Min Act: -0.0001

Data Index: 900290 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1610101 (Python Code)

Max Activating Token Index: 722