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

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

Neuron 1520 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1237032 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1026109 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4180. Min Act: -0.0000

Data Index: 425550 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4232. Min Act: -0.0000

Data Index: 151816 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3945. Min Act: -0.0000

Data Index: 934516 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4033. Min Act: -0.0000

Data Index: 429219 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3902. Min Act: -0.0000

Data Index: 596388 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3618. Min Act: -0.0000

Data Index: 945789 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3660. Min Act: -0.0000

Data Index: 989442 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3668. Min Act: -0.0000

Data Index: 602104 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3655. Min Act: -0.0000

Data Index: 466663 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1372761 (Python Code)

Max Activating Token Index: 426

Text #12

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3625. Min Act: -0.0000

Data Index: 941177 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3606. Min Act: -0.0000

Data Index: 967660 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3702. Min Act: -0.0000

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3580. Min Act: -0.0000

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1309080 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1344749 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3773. Min Act: -0.0000

Data Index: 309272 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1036069 (C4 (Web Text))

Max Activating Token Index: 101