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

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

Neuron 45 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9052. Min Act: -0.0000

Data Index: 126239 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9083. Min Act: -0.0000

Data Index: 439596 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1173059 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7290. Min Act: -0.0000

Data Index: 417503 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7300. Min Act: -0.0000

Data Index: 372250 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7501. Min Act: -0.0000

Data Index: 443326 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7024. Min Act: -0.0000

Data Index: 854789 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7394. Min Act: -0.0000

Data Index: 49365 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6724. Min Act: -0.0000

Data Index: 133762 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6308. Min Act: -0.0000

Data Index: 563137 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1334324 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6008. Min Act: -0.0000

Data Index: 842377 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.6040. Min Act: -0.0000

Data Index: 35736 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5937. Min Act: -0.0000

Data Index: 861057 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5696. Min Act: -0.0000

Data Index: 371710 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1464131 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5489. Min Act: -0.0000

Data Index: 402232 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5499. Min Act: -0.0000

Data Index: 745074 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5306. Min Act: -0.0000

Data Index: 516559 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.5428. Min Act: -0.0000

Data Index: 342387 (C4 (Web Text))

Max Activating Token Index: 982