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

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

Neuron 3535 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1125834 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1582587 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3782. Min Act: -0.0000

Data Index: 867094 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1574377 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1386429 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3161. Min Act: -0.0000

Data Index: 416066 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3107. Min Act: -0.0000

Data Index: 884317 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3096. Min Act: -0.0000

Data Index: 281811 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2801. Min Act: -0.0000

Data Index: 144330 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2701. Min Act: -0.0000

Data Index: 792750 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1463621 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1294522 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2904. Min Act: -0.0000

Data Index: 266936 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1469666 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1549455 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2904. Min Act: -0.0000

Data Index: 786220 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1359892 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1391561 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2626. Min Act: -0.0000

Data Index: 828335 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1289921 (C4 (Web Text))

Max Activating Token Index: 156