Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3100 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0001

Data Index: 702651 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0671. Min Act: -0.0001

Data Index: 593127 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0682. Min Act: -0.0002

Data Index: 480206 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0547. Min Act: -0.0001

Data Index: 934174 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0578. Min Act: -0.0002

Data Index: 111035 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0548. Min Act: -0.0001

Data Index: 712458 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0493. Min Act: -0.0001

Data Index: 437749 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0522. Min Act: -0.0001

Data Index: 887103 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0435. Min Act: -0.0001

Data Index: 390819 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1313969 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0416. Min Act: -0.0001

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0481. Min Act: -0.0001

Data Index: 785182 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0433. Min Act: -0.0001

Data Index: 176990 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0453. Min Act: -0.0002

Data Index: 988113 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1373661 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0388. Min Act: -0.0001

Data Index: 836815 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0400. Min Act: -0.0001

Data Index: 911456 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0442. Min Act: -0.0001

Data Index: 547782 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0458. Min Act: -0.0001

Data Index: 822630 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0464. Min Act: -0.0001

Data Index: 359995 (C4 (Web Text))

Max Activating Token Index: 188