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

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

Neuron 1044 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7122. Min Range: -4.7122

Max Act: 4.7122. Min Act: -0.0000

Data Index: 551681 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 4.7122. Min Range: -4.7122

Max Act: 4.2744. Min Act: -0.0000

Data Index: 527320 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.9834. Min Act: -0.0000

Data Index: 807547 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.5639. Min Act: -0.0000

Data Index: 628141 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.3423. Min Act: -0.0000

Data Index: 446571 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.2555. Min Act: -0.0000

Data Index: 933278 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.1051. Min Act: -0.0000

Data Index: 1265538 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.9571. Min Act: -0.0000

Data Index: 623958 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.0564. Min Act: -0.0000

Data Index: 599710 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 4.7122. Min Range: -4.7122

Max Act: 3.0332. Min Act: -0.0000

Data Index: 493019 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.8922. Min Act: -0.0000

Data Index: 1210450 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.8788. Min Act: -0.0000

Data Index: 879696 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.7844. Min Act: -0.0000

Data Index: 1154884 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.7455. Min Act: -0.0000

Data Index: 16833 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1305445 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.4641. Min Act: -0.0000

Data Index: 437265 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.6057. Min Act: -0.0000

Data Index: 932754 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.7356. Min Act: -0.0000

Data Index: 1265343 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.5822. Min Act: -0.0000

Data Index: 188475 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 4.7122. Min Range: -4.7122

Max Act: 2.4491. Min Act: -0.0000

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 189