Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9759. Min Act: -0.0000

Data Index: 920094 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0399. Min Act: -0.0000

Data Index: 180890 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0074. Min Act: -0.0000

Data Index: 332831 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1185610 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9987. Min Act: -0.0000

Data Index: 74250 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9914. Min Act: -0.0001

Data Index: 137618 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7983. Min Act: -0.0000

Data Index: 5834 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9217. Min Act: -0.0000

Data Index: 171924 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1317926 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8618. Min Act: -0.0000

Data Index: 645088 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1350187 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8541. Min Act: -0.0000

Data Index: 14725 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8674. Min Act: -0.0000

Data Index: 799248 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8358. Min Act: -0.0000

Data Index: 636717 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.7998. Min Act: -0.0000

Data Index: 880689 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1247106 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1245550 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8411. Min Act: -0.0000

Data Index: 70396 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8804. Min Act: -0.0000

Data Index: 473294 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8584. Min Act: -0.0000

Data Index: 149431 (C4 (Web Text))

Max Activating Token Index: 521