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

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

Neuron 2533 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5638. Min Range: -6.5638

Max Act: 6.5638. Min Act: -0.0000

Data Index: 1118797 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 6.5638. Min Range: -6.5638

Max Act: 6.2593. Min Act: -0.0000

Data Index: 1284356 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.6454. Min Act: -0.0000

Data Index: 614208 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.4681. Min Act: -0.0000

Data Index: 44036 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.4452. Min Act: -0.0000

Data Index: 540644 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.2226. Min Act: -0.0000

Data Index: 958680 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.4089. Min Act: -0.0000

Data Index: 153904 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.3208. Min Act: -0.0000

Data Index: 266300 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.2466. Min Act: -0.0000

Data Index: 517429 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.1950. Min Act: -0.0000

Data Index: 1033321 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.8742. Min Act: -0.0000

Data Index: 435813 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.9389. Min Act: -0.0000

Data Index: 364429 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.7126. Min Act: -0.0000

Data Index: 1105923 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.8823. Min Act: -0.0000

Data Index: 1035961 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.0842. Min Act: -0.0000

Data Index: 1091131 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.9006. Min Act: -0.0000

Data Index: 1109078 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 6.5638. Min Range: -6.5638

Max Act: 5.0179. Min Act: -0.0000

Data Index: 1134419 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.8417. Min Act: -0.0000

Data Index: 274963 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.9807. Min Act: -0.0000

Data Index: 892726 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 6.5638. Min Range: -6.5638

Max Act: 4.6888. Min Act: -0.0000

Data Index: 622177 (C4 (Web Text))

Max Activating Token Index: 600