Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1195557 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1027480 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0574. Min Act: -0.0001

Data Index: 124928 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1070372 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1035224 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1036339 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0568. Min Act: -0.0002

Data Index: 402352 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0557. Min Act: -0.0002

Data Index: 74332 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0567. Min Act: -0.0002

Data Index: 235444 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1235868 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0553. Min Act: -0.0002

Data Index: 262132 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0542. Min Act: -0.0002

Data Index: 170598 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0535. Min Act: -0.0002

Data Index: 894662 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0524. Min Act: -0.0002

Data Index: 367248 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0561. Min Act: -0.0002

Data Index: 22692 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1222745 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1290508 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1259435 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0527. Min Act: -0.0002

Data Index: 592202 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1269615 (C4 (Web Text))

Max Activating Token Index: 824