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

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

Neuron 169 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: 0.0466. Min Range: -0.0466

Max Act: 0.0466. Min Act: -0.0005

Data Index: 562508 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1249740 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1211589 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0427. Min Act: -0.0005

Data Index: 836494 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1174758 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1193800 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0408. Min Act: -0.0005

Data Index: 669296 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0410. Min Act: -0.0005

Data Index: 314270 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0422. Min Act: -0.0005

Data Index: 647940 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0392. Min Act: -0.0005

Data Index: 801057 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0412. Min Act: -0.0005

Data Index: 730673 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0435. Min Act: -0.0005

Data Index: 985621 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1076985 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0396. Min Act: -0.0005

Data Index: 166387 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0418. Min Act: -0.0005

Data Index: 133436 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0401. Min Act: -0.0005

Data Index: 880749 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1102491 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0397. Min Act: -0.0005

Data Index: 139019 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0404. Min Act: -0.0005

Data Index: 741079 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0466. Min Range: -0.0466

Max Act: 0.0373. Min Act: -0.0005

Data Index: 1116383 (C4 (Web Text))

Max Activating Token Index: 423