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

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

Neuron 1471 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4814. Min Range: -9.4814

Max Act: 9.4814. Min Act: -0.1700

Data Index: 677937 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 9.4814. Min Range: -9.4814

Max Act: 9.4189. Min Act: -0.1700

Data Index: 944190 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 9.4814. Min Range: -9.4814

Max Act: 9.0127. Min Act: -0.1700

Data Index: 708482 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.9189. Min Act: -0.1700

Data Index: 998765 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7939. Min Act: -0.1700

Data Index: 258286 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7627. Min Act: -0.1700

Data Index: 486714 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7627. Min Act: -0.1699

Data Index: 1109551 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7314. Min Act: -0.1700

Data Index: 1175817 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7627. Min Act: -0.1700

Data Index: 980644 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7002. Min Act: -0.1700

Data Index: 641496 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.6689. Min Act: -0.1700

Data Index: 929660 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7002. Min Act: -0.1700

Data Index: 741011 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.7939. Min Act: -0.1699

Data Index: 509886 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.6377. Min Act: -0.1700

Data Index: 389339 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.5752. Min Act: -0.1700

Data Index: 274496 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.5752. Min Act: -0.1700

Data Index: 1086986 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.6689. Min Act: -0.1700

Data Index: 518972 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.5127. Min Act: -0.1700

Data Index: 862106 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.5752. Min Act: -0.1699

Data Index: 437264 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 9.4814. Min Range: -9.4814

Max Act: 8.4814. Min Act: -0.1700

Data Index: 602739 (C4 (Web Text))

Max Activating Token Index: 756