Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2764 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.5357. Min Act: -0.0003

Data Index: 245665 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4387. Min Act: -0.0003

Data Index: 757868 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4854. Min Act: -0.0003

Data Index: 378358 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4257. Min Act: -0.0003

Data Index: 1044102 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4345. Min Act: -0.0003

Data Index: 1066213 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4696. Min Act: -0.0003

Data Index: 1041565 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4692. Min Act: -0.0003

Data Index: 120917 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4452. Min Act: -0.0003

Data Index: 1032711 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4137. Min Act: -0.0003

Data Index: 1255529 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3329. Min Act: -0.0003

Data Index: 400191 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4013. Min Act: -0.0003

Data Index: 1182606 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4016. Min Act: -0.0003

Data Index: 692588 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4017. Min Act: -0.0003

Data Index: 1065203 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3897. Min Act: -0.0003

Data Index: 514450 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3746. Min Act: -0.0003

Data Index: 1144938 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3989. Min Act: -0.0003

Data Index: 1067639 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3579. Min Act: -0.0003

Data Index: 800707 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.4089. Min Act: -0.0003

Data Index: 663397 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3946. Min Act: -0.0003

Data Index: 580924 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.5357. Min Range: -0.5357

Max Act: 0.3644. Min Act: -0.0003

Data Index: 720628 (C4 (Web Text))

Max Activating Token Index: 853