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

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

Neuron 4751 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: 3.5222. Min Range: -3.5222

Max Act: 3.2481. Min Act: -0.0000

Data Index: 453543 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.3847. Min Act: -0.0000

Data Index: 1046694 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.5222. Min Act: -0.0000

Data Index: 966347 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1371. Min Act: -0.0000

Data Index: 548097 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.2606. Min Act: -0.0000

Data Index: 1266906 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.3602. Min Act: -0.0000

Data Index: 570684 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.2002. Min Act: -0.0000

Data Index: 1256112 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1769. Min Act: -0.0000

Data Index: 473845 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1307948 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1463. Min Act: -0.0000

Data Index: 1098271 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1354. Min Act: -0.0000

Data Index: 666993 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1081. Min Act: -0.0000

Data Index: 71067 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1131. Min Act: -0.0000

Data Index: 834507 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1044. Min Act: -0.0000

Data Index: 469948 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.3743. Min Act: -0.0000

Data Index: 200885 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 3.5222. Min Range: -3.5222

Max Act: 3.1811. Min Act: -0.0000

Data Index: 43960 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.9318. Min Act: -0.0000

Data Index: 701599 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.7348. Min Act: -0.0000

Data Index: 18500 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.7728. Min Act: -0.0000

Data Index: 841356 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.5222. Min Range: -3.5222

Max Act: 2.8649. Min Act: -0.0000

Data Index: 481288 (C4 (Web Text))

Max Activating Token Index: 356