Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 172 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0001

Data Index: 484376 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2078. Min Act: -0.0001

Data Index: 803836 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2375. Min Act: -0.0001

Data Index: 551005 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1046785 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1310036 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1862. Min Act: -0.0001

Data Index: 79101 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2047. Min Act: -0.0001

Data Index: 285312 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1961. Min Act: -0.0001

Data Index: 918801 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1233268 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1101407 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1951. Min Act: -0.0001

Data Index: 309251 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1168973 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1906. Min Act: -0.0001

Data Index: 860444 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1266500 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1907. Min Act: -0.0001

Data Index: 759782 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1823. Min Act: -0.0001

Data Index: 698 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1885. Min Act: -0.0001

Data Index: 700681 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1753. Min Act: -0.0001

Data Index: 697266 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1885. Min Act: -0.0001

Data Index: 372737 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1784. Min Act: -0.0001

Data Index: 83235 (C4 (Web Text))

Max Activating Token Index: 142