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

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

Neuron 625 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: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0001

Data Index: 690168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0497. Min Act: -0.0001

Data Index: 570577 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1599511 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0472. Min Act: -0.0001

Data Index: 794047 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0457. Min Act: -0.0001

Data Index: 679834 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0437. Min Act: -0.0001

Data Index: 57447 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0422. Min Act: -0.0000

Data Index: 434209 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0374. Min Act: -0.0001

Data Index: 997359 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1249292 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0429. Min Act: -0.0001

Data Index: 224321 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0416. Min Act: -0.0002

Data Index: 124177 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0411. Min Act: -0.0001

Data Index: 427639 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0425. Min Act: -0.0001

Data Index: 314213 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0406. Min Act: -0.0001

Data Index: 899960 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0414. Min Act: -0.0001

Data Index: 54570 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1203992 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1293215 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0401. Min Act: -0.0002

Data Index: 787194 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0411. Min Act: -0.0001

Data Index: 796047 (C4 (Web Text))

Max Activating Token Index: 419