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

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

Neuron 3883 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: 0.8366. Min Range: -0.8366

Max Act: 0.8366. Min Act: -0.0001

Data Index: 377104 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.8053. Min Act: -0.0000

Data Index: 353349 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7936. Min Act: -0.0001

Data Index: 1197248 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7771. Min Act: -0.0001

Data Index: 273810 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7853. Min Act: -0.0001

Data Index: 719610 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7492. Min Act: -0.0001

Data Index: 1129032 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7632. Min Act: -0.0001

Data Index: 931956 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7388. Min Act: -0.0001

Data Index: 919108 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7618. Min Act: -0.0001

Data Index: 1292479 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7555. Min Act: -0.0001

Data Index: 452496 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6927. Min Act: -0.0000

Data Index: 484525 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7208. Min Act: -0.0001

Data Index: 128075 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7604. Min Act: -0.0000

Data Index: 130217 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7516. Min Act: -0.0001

Data Index: 346334 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7043. Min Act: -0.0001

Data Index: 456378 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7078. Min Act: -0.0001

Data Index: 778200 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7059. Min Act: -0.0001

Data Index: 565098 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7064. Min Act: -0.0001

Data Index: 325966 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6696. Min Act: -0.0000

Data Index: 227748 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6915. Min Act: -0.0001

Data Index: 733060 (C4 (Web Text))

Max Activating Token Index: 930