Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.9150. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.1187. Min Act: -0.0000

Data Index: 278926 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.1280. Min Act: -0.0000

Data Index: 831639 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1149133 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9817. Min Act: -0.0000

Data Index: 350278 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9701. Min Act: -0.0000

Data Index: 27241 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9542. Min Act: -0.0000

Data Index: 632488 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.8920. Min Act: -0.0000

Data Index: 863027 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9465. Min Act: -0.0000

Data Index: 894665 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1016997 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9337. Min Act: -0.0000

Data Index: 750137 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9366. Min Act: -0.0000

Data Index: 620786 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9060. Min Act: -0.0000

Data Index: 207586 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9307. Min Act: -0.0000

Data Index: 242456 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.8953. Min Act: -0.0000

Data Index: 377422 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1117454 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.9126. Min Act: -0.0000

Data Index: 531100 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.8580. Min Act: -0.0000

Data Index: 491754 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.9150. Min Range: -1.9150

Max Act: 0.8825. Min Act: -0.0000

Data Index: 803233 (C4 (Web Text))

Max Activating Token Index: 175