Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 488 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0002

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5481. Min Act: -0.0002

Data Index: 693417 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5571. Min Act: -0.0002

Data Index: 1147391 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5218. Min Act: -0.0002

Data Index: 539570 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5457. Min Act: -0.0002

Data Index: 8528 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5322. Min Act: -0.0002

Data Index: 1253152 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5330. Min Act: -0.0002

Data Index: 1183271 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4885. Min Act: -0.0002

Data Index: 585428 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5109. Min Act: -0.0002

Data Index: 1139218 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4979. Min Act: -0.0002

Data Index: 684161 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4902. Min Act: -0.0002

Data Index: 1144128 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4561. Min Act: -0.0002

Data Index: 1232805 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4797. Min Act: -0.0002

Data Index: 69987 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4881. Min Act: -0.0002

Data Index: 653073 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4721. Min Act: -0.0002

Data Index: 676207 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4892. Min Act: -0.0002

Data Index: 492423 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4799. Min Act: -0.0002

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4844. Min Act: -0.0002

Data Index: 768601 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4817. Min Act: -0.0002

Data Index: 372399 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4648. Min Act: -0.0002

Data Index: 274385 (C4 (Web Text))

Max Activating Token Index: 638