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

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

Neuron 997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.4492. Min Act: -0.1700

Data Index: 205794 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.2930. Min Act: -0.1700

Data Index: 190493 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1992. Min Act: -0.1700

Data Index: 276217 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.2930. Min Act: -0.1700

Data Index: 1103246 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1367. Min Act: -0.1700

Data Index: 747803 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1367. Min Act: -0.1700

Data Index: 19013 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1680. Min Act: -0.1700

Data Index: 817299 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 42039 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0742. Min Act: -0.1700

Data Index: 367865 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0742. Min Act: -0.1700

Data Index: 958122 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 767917 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0742. Min Act: -0.1700

Data Index: 580182 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0742. Min Act: -0.1700

Data Index: 418879 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1367. Min Act: -0.1700

Data Index: 1088693 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 36365 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 553135 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.1055. Min Act: -0.1700

Data Index: 1127058 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 928580 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0742. Min Act: -0.1700

Data Index: 673764 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 5.4492. Min Range: -5.4492

Max Act: 5.0430. Min Act: -0.1700

Data Index: 859334 (C4 (Web Text))

Max Activating Token Index: 865