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

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

Neuron 3490 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4792. Min Act: -0.0001

Data Index: 470298 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4565. Min Act: -0.0000

Data Index: 734238 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4640. Min Act: -0.0001

Data Index: 1309370 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4619. Min Act: -0.0000

Data Index: 649040 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4308. Min Act: -0.0000

Data Index: 908591 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1040969 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4000. Min Act: -0.0000

Data Index: 658632 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3981. Min Act: -0.0000

Data Index: 18240 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3941. Min Act: -0.0000

Data Index: 660662 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3937. Min Act: -0.0000

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3989. Min Act: -0.0000

Data Index: 967413 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.4086. Min Act: -0.0000

Data Index: 304463 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3579. Min Act: -0.0001

Data Index: 862055 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1073543 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3654. Min Act: -0.0001

Data Index: 1116366 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3645. Min Act: -0.0000

Data Index: 4419 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3566. Min Act: -0.0000

Data Index: 957507 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3569. Min Act: -0.0001

Data Index: 412446 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3567. Min Act: -0.0000

Data Index: 814404 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.4792. Min Range: -0.4792

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1299661 (C4 (Web Text))

Max Activating Token Index: 705