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

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

Neuron 2565 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6753. Min Range: -2.6753

Max Act: 2.6753. Min Act: -0.0000

Data Index: 581223 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.8350. Min Act: -0.0000

Data Index: 798843 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.6396. Min Act: -0.0000

Data Index: 539380 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.5148. Min Act: -0.0000

Data Index: 723681 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.4864. Min Act: -0.0000

Data Index: 181188 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.4939. Min Act: 0.0000

Data Index: 417093 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.4320. Min Act: -0.0000

Data Index: 196603 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.4193. Min Act: -0.0000

Data Index: 412753 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.5164. Min Act: -0.0000

Data Index: 458002 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.3611. Min Act: -0.0000

Data Index: 236395 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2521. Min Act: -0.0000

Data Index: 560956 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1265929 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1218210 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1068759 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2357. Min Act: -0.0000

Data Index: 75202 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.3025. Min Act: -0.0000

Data Index: 530540 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1121198 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.1783. Min Act: -0.0000

Data Index: 460961 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.1113. Min Act: -0.0000

Data Index: 830023 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 2.6753. Min Range: -2.6753

Max Act: 1.1663. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 166