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

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

Neuron 2243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4423. Min Act: -0.0000

Data Index: 766596 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1051835 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1028783 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4159. Min Act: -0.0000

Data Index: 244835 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3853. Min Act: -0.0000

Data Index: 850091 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1102949 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3748. Min Act: -0.0000

Data Index: 419013 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3735. Min Act: -0.0000

Data Index: 73474 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3357. Min Act: -0.0000

Data Index: 450428 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3664. Min Act: -0.0000

Data Index: 665855 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3606. Min Act: -0.0000

Data Index: 797709 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3481. Min Act: -0.0000

Data Index: 167703 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3433. Min Act: -0.0000

Data Index: 631030 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3503. Min Act: -0.0000

Data Index: 234856 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3439. Min Act: -0.0000

Data Index: 464549 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3322. Min Act: -0.0000

Data Index: 974707 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3195. Min Act: -0.0000

Data Index: 480666 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.2955. Min Act: -0.0000

Data Index: 194679 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1280104 (C4 (Web Text))

Max Activating Token Index: 224