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

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

Neuron 1224 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.6283. Min Act: -0.1700

Data Index: 399297 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5657. Min Act: -0.1700

Data Index: 372042 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 909519 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 221490 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5970. Min Act: -0.1700

Data Index: 45062 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 1197264 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5657. Min Act: -0.1700

Data Index: 71685 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 332803 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5657. Min Act: -0.1700

Data Index: 626964 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5030. Min Act: -0.1700

Data Index: 627715 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 472323 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5030. Min Act: -0.1700

Data Index: 708803 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 807090 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 847338 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5030. Min Act: -0.1700

Data Index: 949584 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 974155 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 981711 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 3.6283. Min Range: -3.6283

Max Act: 3.5344. Min Act: -0.1700

Data Index: 1011958 (C4 (Web Text))

Max Activating Token Index: 17