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

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

Neuron 5178 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.9335. Min Act: -0.0000

Data Index: 311461 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.4008. Min Act: -0.0001

Data Index: 254820 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.4955. Min Act: -0.0001

Data Index: 496562 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.1482. Min Act: -0.0001

Data Index: 698420 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.2682. Min Act: -0.0000

Data Index: 361942 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.0233. Min Act: -0.0001

Data Index: 777532 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.9094. Min Act: -0.0001

Data Index: 904701 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.0172. Min Act: -0.0000

Data Index: 542197 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.1389. Min Act: -0.0000

Data Index: 8048 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.3019. Min Act: -0.0000

Data Index: 323561 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.9693. Min Act: -0.0000

Data Index: 466287 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.9637. Min Act: -0.0000

Data Index: 144194 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.1134. Min Act: -0.0001

Data Index: 860833 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.8305. Min Act: -0.0000

Data Index: 669248 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.9105. Min Act: -0.0001

Data Index: 21540 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.7644. Min Act: -0.0001

Data Index: 174077 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.7571. Min Act: -0.0001

Data Index: 513554 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.7480. Min Act: -0.0001

Data Index: 832318 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 3.9335. Min Range: -3.9335

Max Act: 2.8947. Min Act: -0.0000

Data Index: 595722 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 3.9335. Min Range: -3.9335

Max Act: 3.0139. Min Act: -0.0000

Data Index: 453820 (C4 (Web Text))

Max Activating Token Index: 1016