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

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

Neuron 3929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.5636. Min Act: -0.0000

Data Index: 631379 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4772. Min Act: -0.0000

Data Index: 138908 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4672. Min Act: -0.0000

Data Index: 120538 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.5026. Min Act: -0.0000

Data Index: 521623 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1211963 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4347. Min Act: -0.0000

Data Index: 436704 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4265. Min Act: -0.0000

Data Index: 893889 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4682. Min Act: -0.0000

Data Index: 643912 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4385. Min Act: -0.0000

Data Index: 70044 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4451. Min Act: -0.0000

Data Index: 356074 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4452. Min Act: -0.0000

Data Index: 144679 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4197. Min Act: -0.0000

Data Index: 758873 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4184. Min Act: -0.0000

Data Index: 142188 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1357330 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4039. Min Act: -0.0000

Data Index: 46518 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.3962. Min Act: -0.0000

Data Index: 632135 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.3987. Min Act: -0.0000

Data Index: 985163 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.4372. Min Act: -0.0000

Data Index: 990702 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.3749. Min Act: -0.0000

Data Index: 224673 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5636. Min Range: -0.5636

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1188616 (C4 (Web Text))

Max Activating Token Index: 775