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

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

Neuron 824 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: 3.2234. Min Range: -3.2234

Max Act: 3.2234. Min Act: -0.1700

Data Index: 176042 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.2234. Min Act: -0.1700

Data Index: 847607 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1762. Min Act: -0.1700

Data Index: 780174 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1920. Min Act: -0.1700

Data Index: 387437 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1762. Min Act: -0.1700

Data Index: 846606 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1605. Min Act: -0.1700

Data Index: 915186 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1605. Min Act: -0.1700

Data Index: 71791 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1447. Min Act: -0.1700

Data Index: 185142 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1054801 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1447. Min Act: -0.1700

Data Index: 1102372 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.1447. Min Act: -0.1700

Data Index: 1263033 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0817. Min Act: -0.1700

Data Index: 1119165 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1115576 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 869643 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 11277 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 197053 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 410966 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1031223 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0817. Min Act: -0.1700

Data Index: 459320 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 3.2234. Min Range: -3.2234

Max Act: 3.0659. Min Act: -0.1700

Data Index: 287647 (C4 (Web Text))

Max Activating Token Index: 291