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

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

Neuron 384 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3272. Min Act: -0.0001

Data Index: 88621 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1269032 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1358614 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3199. Min Act: -0.0001

Data Index: 553786 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2676. Min Act: -0.0001

Data Index: 652141 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2964. Min Act: -0.0001

Data Index: 573432 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2867. Min Act: -0.0001

Data Index: 704710 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.3076. Min Act: -0.0001

Data Index: 237250 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2927. Min Act: -0.0001

Data Index: 337154 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2530. Min Act: -0.0001

Data Index: 607217 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2706. Min Act: -0.0001

Data Index: 874579 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2544. Min Act: -0.0001

Data Index: 58392 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2644. Min Act: -0.0001

Data Index: 318262 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2612. Min Act: -0.0001

Data Index: 774563 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2590. Min Act: -0.0001

Data Index: 439626 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2520. Min Act: -0.0001

Data Index: 855215 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1060402 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2554. Min Act: -0.0001

Data Index: 217521 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2395. Min Act: -0.0001

Data Index: 201462 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.3445. Min Range: -0.3445

Max Act: 0.2410. Min Act: -0.0001

Data Index: 611060 (C4 (Web Text))

Max Activating Token Index: 585