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

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

Neuron 3765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1193847 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8362. Min Act: -0.0000

Data Index: 755242 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1354791 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7510. Min Act: -0.0000

Data Index: 672623 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6902. Min Act: -0.0000

Data Index: 61271 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6805. Min Act: -0.0000

Data Index: 599306 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1057145 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6458. Min Act: -0.0000

Data Index: 686049 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6916. Min Act: -0.0000

Data Index: 878034 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6464. Min Act: -0.0000

Data Index: 216338 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1180247 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1134871 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6586. Min Act: -0.0000

Data Index: 178123 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1326750 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6545. Min Act: -0.0000

Data Index: 779438 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6343. Min Act: -0.0000

Data Index: 110403 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6502. Min Act: -0.0000

Data Index: 781344 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1262618 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6889. Min Act: -0.0000

Data Index: 419265 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6425. Min Act: -0.0000

Data Index: 815347 (C4 (Web Text))

Max Activating Token Index: 790