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

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

Neuron 98 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: 3.8245. Min Range: -3.8245

Max Act: 3.8245. Min Act: -0.1700

Data Index: 504271 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.7463. Min Act: -0.1700

Data Index: 896512 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.7306. Min Act: -0.1700

Data Index: 1058288 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6837. Min Act: -0.1700

Data Index: 793286 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6524. Min Act: -0.1700

Data Index: 1314303 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6837. Min Act: -0.1700

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6367. Min Act: -0.1700

Data Index: 478881 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6211. Min Act: -0.1700

Data Index: 598532 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5741. Min Act: -0.1700

Data Index: 935574 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6524. Min Act: -0.1700

Data Index: 20608 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6054. Min Act: -0.1700

Data Index: 541178 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6054. Min Act: -0.1700

Data Index: 611683 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5898. Min Act: -0.1700

Data Index: 1152723 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5898. Min Act: -0.1700

Data Index: 1303563 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5584. Min Act: -0.1700

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5428. Min Act: -0.1700

Data Index: 804766 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5584. Min Act: -0.1700

Data Index: 1052232 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.6054. Min Act: -0.1700

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5584. Min Act: -0.1700

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 3.8245. Min Range: -3.8245

Max Act: 3.5584. Min Act: -0.1700

Data Index: 2305 (C4 (Web Text))

Max Activating Token Index: 764