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

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

Neuron 398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.5288. Min Act: -0.0000

Data Index: 28980 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.5110. Min Act: -0.0000

Data Index: 413390 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1216083 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.3765. Min Act: -0.0000

Data Index: 104891 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2274. Min Act: -0.0000

Data Index: 56081 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2693. Min Act: -0.0000

Data Index: 621160 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1235448 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2961. Min Act: -0.0000

Data Index: 307623 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2857. Min Act: -0.0000

Data Index: 512367 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2456. Min Act: -0.0000

Data Index: 38597 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2280. Min Act: -0.0000

Data Index: 990322 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2611. Min Act: -0.0000

Data Index: 962720 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2558. Min Act: -0.0000

Data Index: 961021 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2708. Min Act: -0.0000

Data Index: 445631 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1172443 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2389. Min Act: -0.0000

Data Index: 88813 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2296. Min Act: -0.0000

Data Index: 45828 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.1441. Min Act: -0.0000

Data Index: 642725 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.1887. Min Act: -0.0000

Data Index: 723651 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.5288. Min Range: -1.5288

Max Act: 1.2589. Min Act: -0.0000

Data Index: 726978 (C4 (Web Text))

Max Activating Token Index: 57