Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 881 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0006

Data Index: 441581 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0617. Min Act: -0.0006

Data Index: 824292 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0617. Min Act: -0.0006

Data Index: 647126 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0592. Min Act: -0.0006

Data Index: 1108993 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0591. Min Act: -0.0006

Data Index: 457026 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0612. Min Act: -0.0006

Data Index: 270474 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0599. Min Act: -0.0006

Data Index: 97638 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0574. Min Act: -0.0006

Data Index: 1055794 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0593. Min Act: -0.0006

Data Index: 440203 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0592. Min Act: -0.0006

Data Index: 734651 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1103639 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0565. Min Act: -0.0006

Data Index: 954692 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0549. Min Act: -0.0006

Data Index: 1071090 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0537. Min Act: -0.0006

Data Index: 1254930 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0537. Min Act: -0.0006

Data Index: 363622 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0557. Min Act: -0.0006

Data Index: 709161 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0535. Min Act: -0.0006

Data Index: 679974 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0555. Min Act: -0.0006

Data Index: 246267 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1169549 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0539. Min Act: -0.0006

Data Index: 41671 (C4 (Web Text))

Max Activating Token Index: 22