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

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

Neuron 6070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0284. Min Range: -3.0284

Max Act: 3.0284. Min Act: -0.0000

Data Index: 1368935 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.9080. Min Act: -0.0000

Data Index: 1272907 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.8843. Min Act: -0.0000

Data Index: 1402153 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.8885. Min Act: -0.0000

Data Index: 314724 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1071489 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.6827. Min Act: -0.0000

Data Index: 364354 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.6952. Min Act: -0.0000

Data Index: 1221264 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.5552. Min Act: -0.0000

Data Index: 1184970 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.4633. Min Act: -0.0000

Data Index: 659993 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.5805. Min Act: -0.0000

Data Index: 998074 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.4420. Min Act: -0.0000

Data Index: 226431 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.2636. Min Act: -0.0000

Data Index: 1072607 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.3767. Min Act: -0.0000

Data Index: 395794 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.3679. Min Act: -0.0000

Data Index: 325536 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.3760. Min Act: -0.0000

Data Index: 403761 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1306966 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.2200. Min Act: -0.0000

Data Index: 1251193 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.1318. Min Act: -0.0000

Data Index: 806370 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.1853. Min Act: -0.0000

Data Index: 188337 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.0284. Min Range: -3.0284

Max Act: 2.3102. Min Act: -0.0000

Data Index: 413865 (C4 (Web Text))

Max Activating Token Index: 662