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

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

Neuron 1315 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.1306. Min Act: -0.1700

Data Index: 47648 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1026098 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0675. Min Act: -0.1700

Data Index: 845799 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0675. Min Act: -0.1700

Data Index: 293628 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0675. Min Act: -0.1700

Data Index: 229072 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0359. Min Act: -0.1700

Data Index: 1193231 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 79977 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0359. Min Act: -0.1700

Data Index: 709226 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 765819 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 986463 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 141920 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 958794 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 443931 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 198542 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 211335 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0359. Min Act: -0.1700

Data Index: 1080433 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0043. Min Act: -0.1700

Data Index: 842354 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0201. Min Act: -0.1700

Data Index: 627503 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.1306. Min Range: -3.1306

Max Act: 2.9885. Min Act: -0.1700

Data Index: 901143 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.1306. Min Range: -3.1306

Max Act: 3.0043. Min Act: -0.1700

Data Index: 665885 (C4 (Web Text))

Max Activating Token Index: 306