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

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

Neuron 708 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.3536. Min Act: -0.1700

Data Index: 993492 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.3222. Min Act: -0.1700

Data Index: 443855 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.3065. Min Act: -0.1700

Data Index: 1082675 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.2122. Min Act: -0.1700

Data Index: 478528 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1335. Min Act: -0.1700

Data Index: 51360 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1335. Min Act: -0.1700

Data Index: 426653 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1335. Min Act: -0.1700

Data Index: 724252 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1335. Min Act: -0.1700

Data Index: 284517 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1177. Min Act: -0.1700

Data Index: 265466 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1177. Min Act: -0.1700

Data Index: 242914 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.1177. Min Act: -0.1700

Data Index: 1282000 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0704. Min Act: -0.1700

Data Index: 1328695 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0862. Min Act: -0.1700

Data Index: 1048499 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0862. Min Act: -0.1700

Data Index: 658251 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0546. Min Act: -0.1700

Data Index: 309504 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0862. Min Act: -0.1700

Data Index: 225207 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0704. Min Act: -0.1700

Data Index: 1353733 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0546. Min Act: -0.1700

Data Index: 565145 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0862. Min Act: -0.1700

Data Index: 867420 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 3.3536. Min Range: -3.3536

Max Act: 3.0704. Min Act: -0.1700

Data Index: 478594 (C4 (Web Text))

Max Activating Token Index: 332