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

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

Neuron 3258 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4643. Min Range: -3.4643

Max Act: 3.4643. Min Act: -0.0000

Data Index: 680081 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.4643. Min Range: -3.4643

Max Act: 3.1016. Min Act: -0.0000

Data Index: 52558 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.5648. Min Act: -0.0000

Data Index: 426621 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.2776. Min Act: -0.0000

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.3358. Min Act: -0.0000

Data Index: 1390248 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.3047. Min Act: -0.0000

Data Index: 614204 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.2057. Min Act: -0.0000

Data Index: 839664 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.1235. Min Act: -0.0000

Data Index: 107584 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.0473. Min Act: -0.0000

Data Index: 1126372 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9253. Min Act: -0.0000

Data Index: 180941 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.1058. Min Act: -0.0000

Data Index: 737723 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1091795 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 3.4643. Min Range: -3.4643

Max Act: 2.0450. Min Act: -0.0000

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9625. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9374. Min Act: -0.0000

Data Index: 870620 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9407. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9205. Min Act: -0.0000

Data Index: 15712 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.9058. Min Act: -0.0000

Data Index: 1162748 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.7912. Min Act: -0.0000

Data Index: 297934 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.4643. Min Range: -3.4643

Max Act: 1.8671. Min Act: -0.0000

Data Index: 32437 (C4 (Web Text))

Max Activating Token Index: 17