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

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

Neuron 2896 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: 0.6472. Min Range: -0.6472

Max Act: 0.6472. Min Act: -0.0000

Data Index: 136137 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1133565 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5309. Min Act: -0.0000

Data Index: 625052 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4756. Min Act: -0.0000

Data Index: 940677 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4626. Min Act: 0.0000

Data Index: 796431 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4217. Min Act: -0.0000

Data Index: 567052 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4633. Min Act: -0.0000

Data Index: 838190 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4086. Min Act: -0.0000

Data Index: 741912 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4670. Min Act: -0.0000

Data Index: 937887 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4027. Min Act: -0.0000

Data Index: 20896 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3768. Min Act: -0.0000

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4236. Min Act: -0.0000

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1064502 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3663. Min Act: -0.0000

Data Index: 346982 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1281150 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3918. Min Act: -0.0000

Data Index: 131228 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3648. Min Act: -0.0000

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3886. Min Act: -0.0000

Data Index: 826497 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1077818 (C4 (Web Text))

Max Activating Token Index: 718