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

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

Neuron 1282 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: 5.3418. Min Range: -5.3418

Max Act: 5.3418. Min Act: -0.1700

Data Index: 1000738 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.3106. Min Act: -0.1700

Data Index: 99232 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.2793. Min Act: -0.1700

Data Index: 931692 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.2481. Min Act: -0.1700

Data Index: 969697 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1856. Min Act: -0.1700

Data Index: 720917 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1856. Min Act: -0.1700

Data Index: 774748 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.2168. Min Act: -0.1700

Data Index: 554195 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1856. Min Act: -0.1700

Data Index: 717288 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1231. Min Act: -0.1700

Data Index: 1091804 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.2168. Min Act: -0.1700

Data Index: 268868 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1543. Min Act: -0.1700

Data Index: 421572 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1231. Min Act: -0.1700

Data Index: 703772 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1543. Min Act: -0.1700

Data Index: 881917 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1856. Min Act: -0.1700

Data Index: 425523 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1231. Min Act: -0.1700

Data Index: 349493 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1231. Min Act: -0.1700

Data Index: 898034 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1543. Min Act: -0.1700

Data Index: 1083196 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.0606. Min Act: -0.1700

Data Index: 369069 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.0606. Min Act: -0.1700

Data Index: 1057000 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.3418. Min Range: -5.3418

Max Act: 5.1231. Min Act: -0.1700

Data Index: 824945 (C4 (Web Text))

Max Activating Token Index: 259