Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.4120. Min Act: -0.0002

Data Index: 1328579 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1754. Min Act: -0.0001

Data Index: 1195767 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.2322. Min Act: -0.0002

Data Index: 1299441 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1236. Min Act: -0.0001

Data Index: 848634 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.4120. Min Range: -1.4120

Max Act: 0.9192. Min Act: -0.0001

Data Index: 774409 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.2079. Min Act: -0.0002

Data Index: 89230 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1519. Min Act: -0.0001

Data Index: 467719 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1618. Min Act: -0.0001

Data Index: 254529 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1102. Min Act: -0.0001

Data Index: 955361 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1058. Min Act: -0.0002

Data Index: 1188426 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1619. Min Act: -0.0001

Data Index: 873019 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0682. Min Act: -0.0001

Data Index: 91501 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1209. Min Act: -0.0002

Data Index: 940801 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0760. Min Act: -0.0002

Data Index: 1263579 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1136. Min Act: -0.0002

Data Index: 359397 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.1384. Min Act: -0.0001

Data Index: 970662 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0477. Min Act: -0.0002

Data Index: 349532 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0707. Min Act: -0.0001

Data Index: 676047 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0636. Min Act: -0.0002

Data Index: 516185 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.4120. Min Range: -1.4120

Max Act: 1.0068. Min Act: -0.0001

Data Index: 843909 (C4 (Web Text))

Max Activating Token Index: 142