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

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

Neuron 1529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.8275. Min Act: -0.0001

Data Index: 863823 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7632. Min Act: -0.0001

Data Index: 1305411 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7279. Min Act: -0.0001

Data Index: 518800 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7033. Min Act: -0.0001

Data Index: 769322 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5903. Min Act: -0.0001

Data Index: 1133582 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.8729. Min Act: -0.0001

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6683. Min Act: -0.0001

Data Index: 380843 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.3314. Min Act: -0.0001

Data Index: 705496 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6875. Min Act: -0.0001

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6637. Min Act: -0.0001

Data Index: 95686 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7572. Min Act: -0.0001

Data Index: 759707 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6492. Min Act: -0.0001

Data Index: 898486 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6439. Min Act: -0.0001

Data Index: 550977 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5466. Min Act: -0.0001

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6270. Min Act: -0.0001

Data Index: 1355757 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.7102. Min Act: -0.0001

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.4867. Min Act: -0.0001

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5562. Min Act: -0.0001

Data Index: 1210622 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5377. Min Act: -0.0001

Data Index: 112848 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5261. Min Act: -0.0001

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 208