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

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

Neuron 3050 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: 0.4126. Min Range: -0.4126

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1044533 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.4126. Min Act: -0.0000

Data Index: 211168 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.3085. Min Act: -0.0000

Data Index: 752445 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2818. Min Act: -0.0000

Data Index: 380950 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1208544 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1563509 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1239814 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2592. Min Act: -0.0000

Data Index: 29802 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2599. Min Act: -0.0000

Data Index: 770031 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1328481 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2560. Min Act: -0.0000

Data Index: 270323 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2643. Min Act: -0.0000

Data Index: 410967 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2303. Min Act: -0.0000

Data Index: 700722 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2321. Min Act: -0.0000

Data Index: 950770 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2440. Min Act: -0.0000

Data Index: 600438 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2420. Min Act: -0.0000

Data Index: 508532 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1569553 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2330. Min Act: -0.0000

Data Index: 237769 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2231. Min Act: -0.0000

Data Index: 227226 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2157. Min Act: -0.0000

Data Index: 183708 (C4 (Web Text))

Max Activating Token Index: 826