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

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

Neuron 488 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2990. Min Act: -0.1700

Data Index: 568097 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2676. Min Act: -0.1700

Data Index: 834407 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2362. Min Act: -0.1700

Data Index: 249565 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2047. Min Act: -0.1700

Data Index: 1120597 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2204. Min Act: -0.1700

Data Index: 36697 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.2047. Min Act: -0.1700

Data Index: 1003308 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1233412 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1575. Min Act: -0.1700

Data Index: 1304865 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1364991 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1418. Min Act: -0.1700

Data Index: 82940 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1418. Min Act: -0.1700

Data Index: 366812 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 385981 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 1275845 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.0945. Min Act: -0.1700

Data Index: 947517 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 53255 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 142464 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.0787. Min Act: -0.1700

Data Index: 723992 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.0787. Min Act: -0.1700

Data Index: 856814 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 1189596 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 3.2990. Min Range: -3.2990

Max Act: 3.1102. Min Act: -0.1700

Data Index: 396111 (C4 (Web Text))

Max Activating Token Index: 559