Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5340. Min Act: -0.0001

Data Index: 320873 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4845. Min Act: -0.0001

Data Index: 303605 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1105152 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3650. Min Act: -0.0001

Data Index: 636966 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1041618 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4557. Min Act: -0.0001

Data Index: 792226 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4246. Min Act: -0.0001

Data Index: 807933 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4303. Min Act: -0.0001

Data Index: 202423 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3136. Min Act: -0.0001

Data Index: 339623 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1077878 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3827. Min Act: -0.0001

Data Index: 721946 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3937. Min Act: -0.0001

Data Index: 218490 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4302. Min Act: -0.0001

Data Index: 811784 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3874. Min Act: -0.0001

Data Index: 304638 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3718. Min Act: -0.0001

Data Index: 456889 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1005609 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3602. Min Act: -0.0001

Data Index: 451953 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3589. Min Act: -0.0001

Data Index: 647239 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4090. Min Act: -0.0001

Data Index: 564284 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3960. Min Act: -0.0001

Data Index: 621133 (C4 (Web Text))

Max Activating Token Index: 727