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

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

Neuron 632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7915. Min Act: -0.1700

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7602. Min Act: -0.1700

Data Index: 1077629 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7446. Min Act: -0.1700

Data Index: 1060431 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7602. Min Act: -0.1700

Data Index: 666821 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7446. Min Act: -0.1700

Data Index: 1269551 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6976. Min Act: -0.1700

Data Index: 221600 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6663. Min Act: -0.1700

Data Index: 922636 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6976. Min Act: -0.1700

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.7133. Min Act: -0.1700

Data Index: 665022 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6507. Min Act: -0.1700

Data Index: 808136 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6350. Min Act: -0.1700

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6350. Min Act: -0.1700

Data Index: 1204067 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6350. Min Act: -0.1700

Data Index: 832646 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6194. Min Act: -0.1700

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6507. Min Act: -0.1700

Data Index: 922385 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6194. Min Act: -0.1700

Data Index: 502125 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6037. Min Act: -0.1700

Data Index: 143550 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6037. Min Act: -0.1700

Data Index: 835091 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.5880. Min Act: -0.1700

Data Index: 1215703 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 3.7915. Min Range: -3.7915

Max Act: 3.6037. Min Act: -0.1700

Data Index: 103462 (C4 (Web Text))

Max Activating Token Index: 872