Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1565 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.2422. Min Act: -0.1700

Data Index: 120786 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1817. Min Act: -0.1700

Data Index: 220343 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0853. Min Act: -0.1700

Data Index: 929769 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0866. Min Act: -0.1699

Data Index: 514818 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0648. Min Act: -0.1699

Data Index: 1220280 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0413. Min Act: -0.1700

Data Index: 500484 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0455. Min Act: -0.1700

Data Index: 755059 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0479. Min Act: -0.1700

Data Index: 1057286 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0458. Min Act: -0.1700

Data Index: 797519 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0084. Min Act: -0.1700

Data Index: 791 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 3.2422. Min Range: -3.2422

Max Act: 2.9998. Min Act: -0.1699

Data Index: 822368 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0256. Min Act: -0.1700

Data Index: 95050 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0069. Min Act: -0.1700

Data Index: 840734 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0088. Min Act: -0.1700

Data Index: 704632 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0081. Min Act: -0.1700

Data Index: 963394 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0153. Min Act: -0.1699

Data Index: 1102086 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0091. Min Act: -0.1700

Data Index: 1020640 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 3.2422. Min Range: -3.2422

Max Act: 2.9948. Min Act: -0.1700

Data Index: 566326 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.2422. Min Range: -3.2422

Max Act: 2.9975. Min Act: -0.1700

Data Index: 527218 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 3.2422. Min Range: -3.2422

Max Act: 2.9989. Min Act: -0.1696

Data Index: 654065 (C4 (Web Text))

Max Activating Token Index: 154