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

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

Neuron 712 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.3634. Min Act: -0.1700

Data Index: 27746 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.3322. Min Act: -0.1700

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.3009. Min Act: -0.1700

Data Index: 594760 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.3322. Min Act: -0.1700

Data Index: 86620 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.2072. Min Act: -0.1700

Data Index: 988573 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.1447. Min Act: -0.1700

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.2072. Min Act: -0.1700

Data Index: 737656 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.1759. Min Act: -0.1700

Data Index: 352531 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.1134. Min Act: -0.1700

Data Index: 940530 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.1134. Min Act: -0.1699

Data Index: 574901 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.1134. Min Act: -0.1700

Data Index: 1066599 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0822. Min Act: -0.1700

Data Index: 149656 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0822. Min Act: -0.1700

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0509. Min Act: -0.1700

Data Index: 1194007 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0197. Min Act: -0.1700

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0197. Min Act: -0.1700

Data Index: 473745 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0197. Min Act: -0.1700

Data Index: 437053 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 5.3634. Min Range: -5.3634

Max Act: 5.0197. Min Act: -0.1700

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 5.3634. Min Range: -5.3634

Max Act: 4.9884. Min Act: -0.1700

Data Index: 254480 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 5.3634. Min Range: -5.3634

Max Act: 4.9884. Min Act: -0.1700

Data Index: 169081 (C4 (Web Text))

Max Activating Token Index: 166