Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5380. Min Range: -3.5380

Max Act: 3.4585. Min Act: -0.0000

Data Index: 996523 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.5380. Min Range: -3.5380

Max Act: 3.5380. Min Act: -0.0001

Data Index: 198176 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.5946. Min Act: -0.0000

Data Index: 1238798 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.3077. Min Act: -0.0000

Data Index: 782467 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1327208 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.3222. Min Act: -0.0000

Data Index: 217470 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.1976. Min Act: -0.0000

Data Index: 138516 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.1913. Min Act: -0.0000

Data Index: 305831 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.4046. Min Act: -0.0000

Data Index: 1080160 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.0441. Min Act: -0.0000

Data Index: 723703 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.0471. Min Act: -0.0000

Data Index: 753702 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1058513 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1319391 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.0043. Min Act: -0.0000

Data Index: 249327 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.1014. Min Act: -0.0000

Data Index: 725502 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 3.5380. Min Range: -3.5380

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1183860 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.5380. Min Range: -3.5380

Max Act: 1.9342. Min Act: -0.0001

Data Index: 600247 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 3.5380. Min Range: -3.5380

Max Act: 1.6979. Min Act: -0.0000

Data Index: 211244 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 3.5380. Min Range: -3.5380

Max Act: 1.8898. Min Act: -0.0000

Data Index: 857259 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 3.5380. Min Range: -3.5380

Max Act: 1.7987. Min Act: -0.0001

Data Index: 224095 (C4 (Web Text))

Max Activating Token Index: 522