Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 917 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5531. Min Act: -0.1700

Data Index: 790393 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5688. Min Act: -0.1700

Data Index: 93958 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5374. Min Act: -0.1700

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5218. Min Act: -0.1700

Data Index: 546384 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1207944 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5061. Min Act: -0.1700

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4591. Min Act: -0.1700

Data Index: 1303151 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1106643 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5061. Min Act: -0.1700

Data Index: 754923 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4748. Min Act: -0.1700

Data Index: 1246022 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5218. Min Act: -0.1700

Data Index: 1330578 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.5218. Min Act: -0.1700

Data Index: 249295 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4591. Min Act: -0.1700

Data Index: 149964 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1356516 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4748. Min Act: -0.1700

Data Index: 256271 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4591. Min Act: -0.1700

Data Index: 1050579 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4904. Min Act: -0.1700

Data Index: 674197 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4434. Min Act: -0.1700

Data Index: 95203 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.5688. Min Range: -3.5688

Max Act: 3.4434. Min Act: -0.1700

Data Index: 1223185 (C4 (Web Text))

Max Activating Token Index: 824