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

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

Neuron 3291 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: 3.7636. Min Range: -3.7636

Max Act: 3.7636. Min Act: -0.0000

Data Index: 121159 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.7636. Min Range: -3.7636

Max Act: 3.5154. Min Act: -0.0000

Data Index: 1348920 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.9967. Min Act: -0.0000

Data Index: 1196061 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.8550. Min Act: -0.0000

Data Index: 1169472 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.9513. Min Act: -0.0000

Data Index: 790122 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 3.7636. Min Range: -3.7636

Max Act: 3.1402. Min Act: -0.0000

Data Index: 591666 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.7187. Min Act: -0.0000

Data Index: 649148 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.6969. Min Act: -0.0000

Data Index: 911914 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.6909. Min Act: -0.0000

Data Index: 342771 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.5202. Min Act: -0.0000

Data Index: 137239 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.9104. Min Act: -0.0000

Data Index: 242662 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.7440. Min Act: -0.0000

Data Index: 654510 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.5980. Min Act: -0.0000

Data Index: 40670 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.7077. Min Act: -0.0000

Data Index: 1283111 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.5322. Min Act: -0.0000

Data Index: 751555 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.5080. Min Act: -0.0000

Data Index: 641423 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.3931. Min Act: -0.0000

Data Index: 926237 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.4845. Min Act: -0.0000

Data Index: 521702 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1304858 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.7636. Min Range: -3.7636

Max Act: 2.2713. Min Act: -0.0000

Data Index: 396536 (C4 (Web Text))

Max Activating Token Index: 986