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

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

Neuron 3837 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: 5.9357. Min Range: -5.9357

Max Act: 5.9357. Min Act: -0.0000

Data Index: 584471 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.4595. Min Act: -0.0000

Data Index: 1082789 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.4461. Min Act: -0.0000

Data Index: 1036624 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.4333. Min Act: -0.0000

Data Index: 492865 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.1596. Min Act: -0.0000

Data Index: 1345254 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.2475. Min Act: -0.0000

Data Index: 237622 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.0240. Min Act: -0.0000

Data Index: 741139 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.7524. Min Act: -0.0000

Data Index: 795108 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.7300. Min Act: -0.0000

Data Index: 385730 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.8791. Min Act: -0.0000

Data Index: 38671 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.6971. Min Act: -0.0000

Data Index: 1284650 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.8210. Min Act: -0.0000

Data Index: 721694 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.8169. Min Act: -0.0000

Data Index: 292922 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.7555. Min Act: -0.0000

Data Index: 1206900 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.7403. Min Act: -0.0000

Data Index: 1079262 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.5584. Min Act: -0.0000

Data Index: 1315923 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.8913. Min Act: -0.0000

Data Index: 274510 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.7194. Min Act: -0.0000

Data Index: 1088385 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.6893. Min Act: -0.0000

Data Index: 750480 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 5.9357. Min Range: -5.9357

Max Act: 4.6715. Min Act: -0.0000

Data Index: 82542 (C4 (Web Text))

Max Activating Token Index: 299