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

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

Neuron 545 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: 1.9568. Min Range: -1.9568

Max Act: 1.8916. Min Act: -0.0000

Data Index: 878440 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.8502. Min Act: -0.0000

Data Index: 509738 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.9568. Min Act: -0.0001

Data Index: 123058 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.8479. Min Act: -0.0000

Data Index: 182170 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.8337. Min Act: -0.0001

Data Index: 303577 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.7968. Min Act: -0.0000

Data Index: 170565 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5763. Min Act: -0.0000

Data Index: 904669 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.7000. Min Act: -0.0001

Data Index: 976504 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.6872. Min Act: -0.0001

Data Index: 1041777 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.6650. Min Act: -0.0000

Data Index: 492034 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5401. Min Act: -0.0001

Data Index: 118643 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1153992 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.4430. Min Act: -0.0001

Data Index: 325708 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5289. Min Act: -0.0000

Data Index: 739042 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5948. Min Act: -0.0000

Data Index: 563416 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.5095. Min Act: -0.0001

Data Index: 973716 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.6643. Min Act: -0.0001

Data Index: 253665 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1195033 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.4501. Min Act: -0.0001

Data Index: 505506 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 1.9568. Min Range: -1.9568

Max Act: 1.4804. Min Act: -0.0000

Data Index: 1239463 (C4 (Web Text))

Max Activating Token Index: 139