Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 9 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0579. Min Act: -0.0003

Data Index: 813019 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 395923 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0569. Min Act: -0.0003

Data Index: 503631 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0546. Min Act: -0.0003

Data Index: 731601 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0529. Min Act: -0.0003

Data Index: 860516 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0521. Min Act: -0.0004

Data Index: 454651 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0516. Min Act: -0.0003

Data Index: 245022 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1035698 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0499. Min Act: -0.0003

Data Index: 734464 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0516. Min Act: -0.0004

Data Index: 500327 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0506. Min Act: -0.0003

Data Index: 957953 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1247851 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0507. Min Act: -0.0003

Data Index: 788960 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0489. Min Act: -0.0003

Data Index: 869695 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0496. Min Act: -0.0004

Data Index: 815425 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0487. Min Act: -0.0003

Data Index: 462187 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0491. Min Act: -0.0003

Data Index: 30660 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0489. Min Act: -0.0004

Data Index: 1295191 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1201421 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0478. Min Act: -0.0003

Data Index: 926008 (C4 (Web Text))

Max Activating Token Index: 160