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

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

Neuron 2420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.5783. Min Act: -0.0000

Data Index: 600192 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.8934. Min Act: -0.0000

Data Index: 681805 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1137153 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.7672. Min Act: -0.0000

Data Index: 518940 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.7100. Min Act: -0.0001

Data Index: 574698 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.4861. Min Act: -0.0000

Data Index: 643771 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.6072. Min Act: -0.0000

Data Index: 536282 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.4654. Min Act: -0.0000

Data Index: 117341 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.5670. Min Act: -0.0000

Data Index: 625677 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.5700. Min Act: -0.0000

Data Index: 807202 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.4868. Min Act: -0.0000

Data Index: 748493 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.3549. Min Act: -0.0000

Data Index: 917094 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.5896. Min Act: -0.0000

Data Index: 669149 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.2098. Min Act: -0.0000

Data Index: 596152 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.2984. Min Act: -0.0000

Data Index: 813451 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.1699. Min Act: -0.0000

Data Index: 173318 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.1598. Min Act: -0.0000

Data Index: 531419 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 2.8934. Min Range: -2.8934

Max Act: 1.9793. Min Act: -0.0000

Data Index: 695739 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.3162. Min Act: -0.0000

Data Index: 904065 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 2.8934. Min Range: -2.8934

Max Act: 2.1065. Min Act: -0.0000

Data Index: 960330 (C4 (Web Text))

Max Activating Token Index: 682