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

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

Neuron 1102 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: 5.8051. Min Range: -5.8051

Max Act: 5.8051. Min Act: -0.1700

Data Index: 680158 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.5864. Min Act: -0.1700

Data Index: 813833 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.5239. Min Act: -0.1700

Data Index: 637010 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2739. Min Act: -0.1700

Data Index: 267239 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.3676. Min Act: -0.1700

Data Index: 1149724 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.3364. Min Act: -0.1700

Data Index: 1032380 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2739. Min Act: -0.1700

Data Index: 977453 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.3364. Min Act: -0.1700

Data Index: 1184218 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.3051. Min Act: -0.1700

Data Index: 697732 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 1322875 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 642841 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 1164121 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.1801. Min Act: -0.1700

Data Index: 315460 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.1489. Min Act: -0.1700

Data Index: 977462 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2114. Min Act: -0.1700

Data Index: 460412 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 738170 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2739. Min Act: -0.1700

Data Index: 1050310 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 551760 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.2426. Min Act: -0.1700

Data Index: 309601 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 5.8051. Min Range: -5.8051

Max Act: 5.1489. Min Act: -0.1700

Data Index: 317864 (C4 (Web Text))

Max Activating Token Index: 130