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

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

Neuron 6078 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: 3.0568. Min Range: -3.0568

Max Act: 2.8495. Min Act: -0.0001

Data Index: 359496 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.9871. Min Act: -0.0001

Data Index: 421404 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 3.0568. Min Range: -3.0568

Max Act: 3.0568. Min Act: -0.0000

Data Index: 196092 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.6505. Min Act: -0.0000

Data Index: 531560 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.7586. Min Act: -0.0000

Data Index: 1201244 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.5389. Min Act: -0.0001

Data Index: 614655 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4035. Min Act: -0.0001

Data Index: 1106045 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4836. Min Act: -0.0000

Data Index: 118098 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4702. Min Act: -0.0000

Data Index: 279154 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1343836 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4329. Min Act: -0.0000

Data Index: 787216 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.1873. Min Act: -0.0000

Data Index: 774595 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.3951. Min Act: -0.0001

Data Index: 1133606 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4840. Min Act: -0.0000

Data Index: 930350 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4782. Min Act: -0.0000

Data Index: 1320782 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.2096. Min Act: -0.0001

Data Index: 112332 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4285. Min Act: -0.0001

Data Index: 351583 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1070758 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.2995. Min Act: -0.0000

Data Index: 123370 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.2762. Min Act: -0.0000

Data Index: 293724 (C4 (Web Text))

Max Activating Token Index: 92