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

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

Neuron 1223 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: 3.8198. Min Range: -3.8198

Max Act: 3.8198. Min Act: -0.1700

Data Index: 823375 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6946. Min Act: -0.1700

Data Index: 1146902 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.7572. Min Act: -0.1700

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6946. Min Act: -0.1700

Data Index: 556282 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.7572. Min Act: -0.1700

Data Index: 426387 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.7259. Min Act: -0.1700

Data Index: 1123291 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6633. Min Act: -0.1700

Data Index: 243152 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6007. Min Act: -0.1700

Data Index: 1336656 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6007. Min Act: -0.1700

Data Index: 572381 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6007. Min Act: -0.1700

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.6633. Min Act: -0.1700

Data Index: 1127697 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5694. Min Act: -0.1700

Data Index: 709259 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1129588 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5694. Min Act: -0.1700

Data Index: 459874 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5851. Min Act: -0.1700

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5694. Min Act: -0.1700

Data Index: 1053807 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1240926 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5538. Min Act: -0.1700

Data Index: 624266 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5381. Min Act: -0.1700

Data Index: 696726 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.5538. Min Act: -0.1700

Data Index: 365852 (C4 (Web Text))

Max Activating Token Index: 675