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

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

Neuron 3116 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: 5.6491. Min Range: -5.6491

Max Act: 5.3740. Min Act: -0.0000

Data Index: 449415 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.5160. Min Act: -0.0000

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.6491. Min Act: -0.0000

Data Index: 616935 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1962. Min Act: -0.0000

Data Index: 259623 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.0200. Min Act: -0.0000

Data Index: 1117334 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1007. Min Act: -0.0000

Data Index: 767262 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.7139. Min Act: -0.0000

Data Index: 789547 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1690. Min Act: -0.0000

Data Index: 455693 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.0175. Min Act: -0.0000

Data Index: 520551 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.1497. Min Act: -0.0000

Data Index: 1168551 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.9003. Min Act: -0.0000

Data Index: 575399 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.0608. Min Act: -0.0000

Data Index: 1327587 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.6549. Min Act: -0.0000

Data Index: 1220335 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.7973. Min Act: -0.0000

Data Index: 950602 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 5.6491. Min Range: -5.6491

Max Act: 5.0056. Min Act: -0.0000

Data Index: 1354336 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.9077. Min Act: -0.0000

Data Index: 871679 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.7354. Min Act: -0.0000

Data Index: 237805 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.6969. Min Act: -0.0000

Data Index: 1238075 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.6386. Min Act: -0.0000

Data Index: 918723 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 5.6491. Min Range: -5.6491

Max Act: 4.5760. Min Act: -0.0000

Data Index: 456034 (C4 (Web Text))

Max Activating Token Index: 94