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

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

Neuron 4927 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.3922. Min Act: -0.0000

Data Index: 793807 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.2410. Min Act: -0.0000

Data Index: 64570 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0187. Min Act: 0.0000

Data Index: 968629 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.1606. Min Act: 0.0000

Data Index: 670156 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1163109 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0863. Min Act: -0.0000

Data Index: 514688 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0839. Min Act: -0.0000

Data Index: 881850 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0461. Min Act: -0.0000

Data Index: 892445 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1275273 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9726. Min Act: -0.0000

Data Index: 678453 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0740. Min Act: -0.0000

Data Index: 585341 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9648. Min Act: -0.0000

Data Index: 776099 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0087. Min Act: -0.0000

Data Index: 432536 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1354291 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9969. Min Act: -0.0000

Data Index: 982531 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9936. Min Act: -0.0000

Data Index: 188566 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9185. Min Act: -0.0000

Data Index: 429819 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.3922. Min Range: -1.3922

Max Act: 1.0069. Min Act: -0.0000

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9710. Min Act: -0.0000

Data Index: 537347 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.3922. Min Range: -1.3922

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1027014 (C4 (Web Text))

Max Activating Token Index: 813