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

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

Neuron 1568 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: 3.9601. Min Range: -3.9601

Max Act: 3.9601. Min Act: -0.1700

Data Index: 1056586 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.8663. Min Act: -0.1700

Data Index: 587606 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.9132. Min Act: -0.1700

Data Index: 1216356 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.8507. Min Act: -0.1700

Data Index: 1062426 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.8350. Min Act: -0.1700

Data Index: 480392 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.8194. Min Act: -0.1700

Data Index: 213487 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7568. Min Act: -0.1700

Data Index: 165483 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7881. Min Act: -0.1700

Data Index: 92491 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.8194. Min Act: -0.1700

Data Index: 797724 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1041101 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7568. Min Act: -0.1700

Data Index: 437185 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1348814 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1046805 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1337742 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1313245 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.7099. Min Act: -0.1700

Data Index: 637963 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1200721 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6943. Min Act: -0.1700

Data Index: 537775 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6473. Min Act: -0.1700

Data Index: 965811 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 3.9601. Min Range: -3.9601

Max Act: 3.6786. Min Act: -0.1700

Data Index: 889255 (C4 (Web Text))

Max Activating Token Index: 673