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

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

Neuron 1550 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: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0000

Data Index: 150455 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3025. Min Act: -0.0000

Data Index: 202143 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3096. Min Act: -0.0000

Data Index: 219894 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2766. Min Act: -0.0000

Data Index: 629183 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2937. Min Act: -0.0000

Data Index: 221715 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2543. Min Act: -0.0000

Data Index: 917970 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2439. Min Act: -0.0000

Data Index: 442827 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1288418 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2365. Min Act: -0.0000

Data Index: 954115 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1347852 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1918. Min Act: -0.0000

Data Index: 337200 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1893. Min Act: -0.0000

Data Index: 716376 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1881. Min Act: -0.0000

Data Index: 933409 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1846. Min Act: -0.0000

Data Index: 813370 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1942. Min Act: -0.0000

Data Index: 954875 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1060568 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1843. Min Act: -0.0000

Data Index: 782159 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1868. Min Act: -0.0000

Data Index: 794613 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1802. Min Act: -0.0000

Data Index: 696465 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.1581. Min Act: -0.0000

Data Index: 452254 (C4 (Web Text))

Max Activating Token Index: 721