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

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

Neuron 79 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3274. Min Act: 0.0000

Data Index: 882248 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1160756 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3514. Min Act: 0.0000

Data Index: 610920 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3242. Min Act: -0.0000

Data Index: 9836 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1012030 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2973. Min Act: 0.0000

Data Index: 1174254 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1202492 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1342729 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2848. Min Act: 0.0001

Data Index: 182049 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1166708 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2569. Min Act: 0.0001

Data Index: 335469 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2394. Min Act: -0.0000

Data Index: 113098 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2693. Min Act: -0.0000

Data Index: 415583 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2641. Min Act: -0.0000

Data Index: 692866 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2848. Min Act: -0.0000

Data Index: 730730 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1341193 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2867. Min Act: -0.0000

Data Index: 578803 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2494. Min Act: 0.0001

Data Index: 1169404 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2573. Min Act: -0.0000

Data Index: 237061 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.3514. Min Range: -0.3514

Max Act: 0.2548. Min Act: -0.0000

Data Index: 681686 (C4 (Web Text))

Max Activating Token Index: 294