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

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

Neuron 805 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: 3.4292. Min Range: -3.4292

Max Act: 3.4292. Min Act: -0.1700

Data Index: 311440 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.2880. Min Act: -0.1700

Data Index: 1228520 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.2723. Min Act: -0.1700

Data Index: 652360 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.1937. Min Act: -0.1700

Data Index: 774601 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.1307. Min Act: -0.1700

Data Index: 1069115 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0834. Min Act: -0.1700

Data Index: 1278845 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.1149. Min Act: -0.1700

Data Index: 1042386 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1132426 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0834. Min Act: -0.1700

Data Index: 79375 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0676. Min Act: -0.1700

Data Index: 741294 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0676. Min Act: -0.1700

Data Index: 461945 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0518. Min Act: -0.1700

Data Index: 247883 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0834. Min Act: -0.1700

Data Index: 1027319 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1405942 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0518. Min Act: -0.1700

Data Index: 886978 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0360. Min Act: -0.1700

Data Index: 346159 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1326886 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0518. Min Act: -0.1700

Data Index: 223589 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0518. Min Act: -0.1700

Data Index: 423825 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 3.4292. Min Range: -3.4292

Max Act: 3.0360. Min Act: -0.1700

Data Index: 399853 (C4 (Web Text))

Max Activating Token Index: 419