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

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

Neuron 3937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0257. Min Range: -2.0257

Max Act: 2.0257. Min Act: -0.0000

Data Index: 1052170 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.7339. Min Act: -0.0000

Data Index: 952179 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.6457. Min Act: -0.0000

Data Index: 23829 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.6030. Min Act: -0.0000

Data Index: 818155 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1275517 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.5522. Min Act: -0.0000

Data Index: 1299155 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.5469. Min Act: -0.0000

Data Index: 704217 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2634. Min Act: -0.0000

Data Index: 533046 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.3719. Min Act: -0.0000

Data Index: 413817 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2785. Min Act: -0.0000

Data Index: 904327 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.3114. Min Act: -0.0000

Data Index: 28083 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2845. Min Act: -0.0000

Data Index: 999902 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.3213. Min Act: -0.0000

Data Index: 50416 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.1809. Min Act: -0.0000

Data Index: 153303 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1132972 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2212. Min Act: -0.0000

Data Index: 356380 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2011. Min Act: -0.0000

Data Index: 353508 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2133. Min Act: -0.0000

Data Index: 538347 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.1869. Min Act: -0.0000

Data Index: 82146 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.0257. Min Range: -2.0257

Max Act: 1.2776. Min Act: -0.0000

Data Index: 467060 (C4 (Web Text))

Max Activating Token Index: 283