Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1951 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.7003. Min Act: -0.1700

Data Index: 1014101 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6691. Min Act: -0.1700

Data Index: 1047124 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6691. Min Act: -0.1700

Data Index: 261160 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 1287530 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6378. Min Act: -0.1700

Data Index: 703475 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6378. Min Act: -0.1700

Data Index: 402850 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5753. Min Act: -0.1700

Data Index: 845011 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6378. Min Act: -0.1700

Data Index: 444430 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5753. Min Act: -0.1700

Data Index: 423471 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6378. Min Act: -0.1700

Data Index: 630233 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 1008870 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6378. Min Act: -0.1700

Data Index: 1205581 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 1283566 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 562255 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5441. Min Act: -0.1700

Data Index: 64940 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5753. Min Act: -0.1700

Data Index: 818452 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5441. Min Act: -0.1700

Data Index: 451114 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.6066. Min Act: -0.1700

Data Index: 486256 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 5.7003. Min Range: -5.7003

Max Act: 5.5753. Min Act: -0.1700

Data Index: 433579 (C4 (Web Text))

Max Activating Token Index: 635