Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1214135 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1321592 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4517. Min Act: -0.0001

Data Index: 584941 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4665. Min Act: -0.0001

Data Index: 1276907 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1080969 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4239. Min Act: -0.0001

Data Index: 1351768 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4494. Min Act: -0.0001

Data Index: 6390 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4710. Min Act: -0.0001

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4017. Min Act: -0.0001

Data Index: 31794 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1103229 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3796. Min Act: -0.0001

Data Index: 402366 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3406. Min Act: -0.0000

Data Index: 304799 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3180. Min Act: -0.0000

Data Index: 833349 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1149158 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2973. Min Act: -0.0001

Data Index: 978319 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2957. Min Act: -0.0000

Data Index: 679876 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2727. Min Act: -0.0000

Data Index: 102140 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1282406 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2757. Min Act: -0.0000

Data Index: 650227 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1297827 (C4 (Web Text))

Max Activating Token Index: 844