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

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

Neuron 134 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.3507. Min Act: -0.0000

Data Index: 277178 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0379. Min Act: -0.0000

Data Index: 56625 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0449. Min Act: -0.0000

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0042. Min Act: -0.0000

Data Index: 543587 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.8036. Min Act: -0.0000

Data Index: 52092 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.1775. Min Act: -0.0000

Data Index: 1084792 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0739. Min Act: -0.0000

Data Index: 1201901 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0609. Min Act: -0.0000

Data Index: 867899 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0996. Min Act: -0.0000

Data Index: 378037 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.8861. Min Act: -0.0000

Data Index: 111247 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.8613. Min Act: -0.0000

Data Index: 1196683 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0391. Min Act: -0.0000

Data Index: 131410 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.0241. Min Act: -0.0000

Data Index: 1292690 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.9907. Min Act: -0.0000

Data Index: 1188186 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.1761. Min Act: -0.0000

Data Index: 299787 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.8182. Min Act: -0.0000

Data Index: 666375 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.2095. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.9479. Min Act: -0.0000

Data Index: 1264647 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 5.3507. Min Range: -5.3507

Max Act: 4.9619. Min Act: -0.0000

Data Index: 354069 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 5.3507. Min Range: -5.3507

Max Act: 5.1407. Min Act: -0.0000

Data Index: 73044 (C4 (Web Text))

Max Activating Token Index: 289