Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 248 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0764. Min Range: -5.0764

Max Act: 5.0764. Min Act: -0.1700

Data Index: 930138 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.7014. Min Act: -0.1700

Data Index: 1125171 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.7014. Min Act: -0.1700

Data Index: 505050 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6702. Min Act: -0.1700

Data Index: 31537 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6702. Min Act: -0.1700

Data Index: 1213960 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6077. Min Act: -0.1700

Data Index: 1096225 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6077. Min Act: -0.1700

Data Index: 955279 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6389. Min Act: -0.1700

Data Index: 727998 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6389. Min Act: -0.1700

Data Index: 1298173 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6389. Min Act: -0.1700

Data Index: 1223294 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6077. Min Act: -0.1700

Data Index: 562309 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.6389. Min Act: -0.1700

Data Index: 1368929 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5764. Min Act: -0.1700

Data Index: 1060144 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5451. Min Act: -0.1700

Data Index: 701304 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5451. Min Act: -0.1700

Data Index: 1007901 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5764. Min Act: -0.1700

Data Index: 556981 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5451. Min Act: -0.1700

Data Index: 498586 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5764. Min Act: -0.1700

Data Index: 972598 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.5139. Min Act: -0.1700

Data Index: 441124 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 5.0764. Min Range: -5.0764

Max Act: 4.4826. Min Act: -0.1700

Data Index: 535121 (C4 (Web Text))

Max Activating Token Index: 654