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

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

Neuron 3549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.6332. Min Act: -0.0000

Data Index: 76032 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5777. Min Act: -0.0001

Data Index: 417889 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5301. Min Act: -0.0000

Data Index: 45386 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4909. Min Act: -0.0001

Data Index: 93756 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1295785 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4300. Min Act: -0.0001

Data Index: 554612 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4654. Min Act: -0.0001

Data Index: 228410 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1323295 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4455. Min Act: -0.0001

Data Index: 999426 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3466. Min Act: -0.0001

Data Index: 388877 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3794. Min Act: -0.0000

Data Index: 881182 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1174106 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3930. Min Act: -0.0001

Data Index: 1240359 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3933. Min Act: -0.0000

Data Index: 473276 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1276275 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3454. Min Act: -0.0001

Data Index: 1126060 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4182. Min Act: -0.0000

Data Index: 84499 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3317. Min Act: -0.0000

Data Index: 691403 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3721. Min Act: -0.0001

Data Index: 673601 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4102. Min Act: -0.0001

Data Index: 685656 (C4 (Web Text))

Max Activating Token Index: 603