Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 334 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.8419. Min Act: -0.0001

Data Index: 920829 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.8063. Min Act: -0.0001

Data Index: 116064 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.5477. Min Act: -0.0002

Data Index: 853325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.3503. Min Act: -0.0002

Data Index: 877804 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.6016. Min Act: -0.0002

Data Index: 511297 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.3914. Min Act: -0.0001

Data Index: 1305717 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 6.8419. Min Range: -6.8419

Max Act: 6.3826. Min Act: -0.0001

Data Index: 1034881 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.6609. Min Act: -0.0002

Data Index: 61037 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.8409. Min Act: -0.0001

Data Index: 668167 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.9612. Min Act: -0.0001

Data Index: 1276927 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.8573. Min Act: -0.0001

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.6104. Min Act: -0.0002

Data Index: 398275 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.5072. Min Act: -0.0001

Data Index: 363820 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.1695. Min Act: -0.0001

Data Index: 1324407 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.2422. Min Act: -0.0001

Data Index: 572451 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.2441. Min Act: -0.0001

Data Index: 417857 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.4931. Min Act: -0.0001

Data Index: 538434 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.4915. Min Act: -0.0001

Data Index: 689430 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.2670. Min Act: -0.0001

Data Index: 958288 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 6.8419. Min Range: -6.8419

Max Act: 5.0425. Min Act: -0.0001

Data Index: 865387 (C4 (Web Text))

Max Activating Token Index: 27