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

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

Neuron 3176 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1250227 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2930. Min Act: -0.0001

Data Index: 316898 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0001

Data Index: 479061 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1105268 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2429. Min Act: -0.0001

Data Index: 599139 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2476. Min Act: -0.0001

Data Index: 487295 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2419. Min Act: -0.0001

Data Index: 75408 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2265. Min Act: -0.0001

Data Index: 621589 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1647687 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2180. Min Act: -0.0001

Data Index: 291171 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1743. Min Act: -0.0001

Data Index: 563960 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1176078 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1944. Min Act: -0.0001

Data Index: 286775 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1903. Min Act: -0.0001

Data Index: 547706 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2017. Min Act: -0.0001

Data Index: 554642 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2195. Min Act: -0.0001

Data Index: 393761 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1789. Min Act: -0.0001

Data Index: 397620 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1966. Min Act: -0.0001

Data Index: 491132 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2045. Min Act: -0.0001

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1836. Min Act: -0.0001

Data Index: 13318 (C4 (Web Text))

Max Activating Token Index: 1015