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

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

Neuron 4749 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 623498 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0572. Min Act: -0.0002

Data Index: 537933 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0552. Min Act: -0.0002

Data Index: 361394 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0517. Min Act: -0.0002

Data Index: 331196 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1169307 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0510. Min Act: -0.0002

Data Index: 214829 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0499. Min Act: -0.0002

Data Index: 944107 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0497. Min Act: -0.0002

Data Index: 886382 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1003717 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0455. Min Act: -0.0002

Data Index: 126023 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0440. Min Act: -0.0002

Data Index: 651742 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0433. Min Act: -0.0002

Data Index: 325488 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0431. Min Act: -0.0002

Data Index: 376867 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0414. Min Act: -0.0002

Data Index: 68249 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0422. Min Act: -0.0002

Data Index: 616176 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0419. Min Act: -0.0002

Data Index: 296287 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1105989 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0415. Min Act: -0.0002

Data Index: 133264 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1145096 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0419. Min Act: -0.0002

Data Index: 272141 (C4 (Web Text))

Max Activating Token Index: 505