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

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

Neuron 4596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7927. Min Range: -4.7927

Max Act: 4.7927. Min Act: -0.0000

Data Index: 620573 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 4.7927. Min Range: -4.7927

Max Act: 4.6532. Min Act: -0.0000

Data Index: 285747 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.9938. Min Act: -0.0000

Data Index: 333159 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 4.7927. Min Range: -4.7927

Max Act: 4.2199. Min Act: -0.0000

Data Index: 1205279 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.7874. Min Act: -0.0000

Data Index: 1105221 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.3583. Min Act: -0.0000

Data Index: 1022342 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.6795. Min Act: -0.0000

Data Index: 1135337 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.2946. Min Act: -0.0000

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.5317. Min Act: -0.0000

Data Index: 923724 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1349547 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.4056. Min Act: -0.0000

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.3829. Min Act: -0.0000

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.2112. Min Act: -0.0000

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 4.7927. Min Range: -4.7927

Max Act: 2.9832. Min Act: -0.0000

Data Index: 911442 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.2276. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.2021. Min Act: -0.0000

Data Index: 1008580 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.1967. Min Act: -0.0000

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.0608. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.3120. Min Act: -0.0000

Data Index: 527199 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 4.7927. Min Range: -4.7927

Max Act: 3.0099. Min Act: -0.0000

Data Index: 1001153 (C4 (Web Text))

Max Activating Token Index: 658