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

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

Neuron 723 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: 3.2069. Min Range: -3.2069

Max Act: 3.1912. Min Act: -0.1700

Data Index: 1047080 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1122526 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0651. Min Act: -0.1700

Data Index: 1099479 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0651. Min Act: -0.1700

Data Index: 767551 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0967. Min Act: -0.1700

Data Index: 251698 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0335. Min Act: -0.1700

Data Index: 140459 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.2069. Min Range: -3.2069

Max Act: 2.9228. Min Act: -0.1700

Data Index: 147299 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0177. Min Act: -0.1700

Data Index: 1324807 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0335. Min Act: -0.1700

Data Index: 1110068 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1406199 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0177. Min Act: -0.1700

Data Index: 557578 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0177. Min Act: -0.1700

Data Index: 1342698 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.2069. Min Range: -3.2069

Max Act: 2.9703. Min Act: -0.1700

Data Index: 926623 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0177. Min Act: -0.1700

Data Index: 935583 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0335. Min Act: -0.1700

Data Index: 794669 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 3.2069. Min Range: -3.2069

Max Act: 2.9861. Min Act: -0.1700

Data Index: 442182 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1177440 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.2069. Min Range: -3.2069

Max Act: 3.0651. Min Act: -0.1700

Data Index: 1029948 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.2069. Min Range: -3.2069

Max Act: 2.9861. Min Act: -0.1700

Data Index: 958748 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 3.2069. Min Range: -3.2069

Max Act: 2.9861. Min Act: -0.1700

Data Index: 267019 (C4 (Web Text))

Max Activating Token Index: 253