Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 482 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.4573. Min Act: -0.0000

Data Index: 482441 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.4547. Min Act: -0.0000

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1124. Min Act: -0.0000

Data Index: 670378 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1947. Min Act: -0.0000

Data Index: 153105 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1605. Min Act: -0.0000

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.0388. Min Act: -0.0000

Data Index: 297645 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1525. Min Act: -0.0000

Data Index: 83804 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1406. Min Act: -0.0000

Data Index: 434053 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.9833. Min Act: -0.0000

Data Index: 186510 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1245. Min Act: -0.0000

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.9041. Min Act: -0.0000

Data Index: 954122 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.1922. Min Act: -0.0000

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.8330. Min Act: -0.0000

Data Index: 992120 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.4573. Min Range: -3.4573

Max Act: 3.0002. Min Act: -0.0000

Data Index: 516201 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.9527. Min Act: -0.0000

Data Index: 996004 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.9576. Min Act: -0.0000

Data Index: 137369 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.8950. Min Act: -0.0000

Data Index: 274547 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.7489. Min Act: -0.0000

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.8911. Min Act: -0.0000

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.4573. Min Range: -3.4573

Max Act: 2.8706. Min Act: -0.0000

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 355