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

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

Neuron 3412 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0000

Data Index: 57836 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0470. Min Act: -0.0000

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0442. Min Act: -0.0000

Data Index: 1283447 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0431. Min Act: -0.0000

Data Index: 937887 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0447. Min Act: -0.0000

Data Index: 894569 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0413. Min Act: -0.0000

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0384. Min Act: -0.0000

Data Index: 91722 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0330. Min Act: -0.0000

Data Index: 405498 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1496038 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0315. Min Act: -0.0000

Data Index: 1530576 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1587548 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0316. Min Act: -0.0000

Data Index: 898617 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1383791 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0281. Min Act: -0.0000

Data Index: 967190 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0297. Min Act: -0.0000

Data Index: 949316 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0288. Min Act: -0.0000

Data Index: 622190 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0297. Min Act: -0.0000

Data Index: 359759 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1538430 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1602528 (Python Code)

Max Activating Token Index: 727