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

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

Neuron 1240 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.3211. Min Act: -0.1700

Data Index: 1059382 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.3054. Min Act: -0.1700

Data Index: 242994 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1010512 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2897. Min Act: -0.1700

Data Index: 670615 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2583. Min Act: -0.1700

Data Index: 1230112 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2269. Min Act: -0.1700

Data Index: 124482 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 1163526 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2269. Min Act: -0.1700

Data Index: 1131532 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2269. Min Act: -0.1700

Data Index: 49080 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2269. Min Act: -0.1700

Data Index: 1123757 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 1611771 (Python Code)

Max Activating Token Index: 486

Text #11

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.1954. Min Act: -0.1700

Data Index: 998241 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 682436 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.1954. Min Act: -0.1700

Data Index: 166791 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 778329 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.1954. Min Act: -0.1700

Data Index: 1126513 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 189002 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 525924 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.2111. Min Act: -0.1700

Data Index: 1294672 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.3211. Min Range: -3.3211

Max Act: 3.1954. Min Act: -0.1700

Data Index: 1179371 (C4 (Web Text))

Max Activating Token Index: 109