Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 513 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4593. Min Act: -0.0001

Data Index: 566746 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1270012 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3822. Min Act: -0.0001

Data Index: 1366190 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1338301 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1316026 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1341037 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3758. Min Act: -0.0001

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3527. Min Act: -0.0001

Data Index: 644386 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3431. Min Act: -0.0001

Data Index: 447200 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3715. Min Act: -0.0000

Data Index: 490057 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3685. Min Act: -0.0000

Data Index: 300276 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1021783 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1392638 (Python Code)

Max Activating Token Index: 483

Text #13

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1642801 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1082003 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3327. Min Act: -0.0000

Data Index: 377128 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3627. Min Act: -0.0001

Data Index: 840449 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3516. Min Act: -0.0001

Data Index: 1178072 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3501. Min Act: -0.0000

Data Index: 44082 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1097888 (C4 (Web Text))

Max Activating Token Index: 978