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

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

Neuron 515 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: 0.0456. Min Range: -0.0456

Max Act: 0.0455. Min Act: -0.0005

Data Index: 991950 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1015408 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0440. Min Act: -0.0005

Data Index: 236855 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0444. Min Act: -0.0005

Data Index: 368916 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0430. Min Act: -0.0005

Data Index: 496125 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0436. Min Act: -0.0005

Data Index: 24732 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0411. Min Act: -0.0005

Data Index: 383858 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0005

Data Index: 899937 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1434232 (Python Code)

Max Activating Token Index: 975

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0005

Data Index: 526803 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1017121 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0386. Min Act: -0.0005

Data Index: 10113 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1295560 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0386. Min Act: -0.0005

Data Index: 192594 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1035977 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0402. Min Act: -0.0005

Data Index: 137983 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0393. Min Act: -0.0005

Data Index: 770684 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0393. Min Act: -0.0005

Data Index: 89972 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1026718 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0005

Data Index: 50791 (C4 (Web Text))

Max Activating Token Index: 334