Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 24 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.6392. Min Act: -0.1700

Data Index: 931205 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.5766. Min Act: -0.1700

Data Index: 1341303 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.5453. Min Act: -0.1700

Data Index: 489655 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.5296. Min Act: -0.1700

Data Index: 1261170 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.5139. Min Act: -0.1700

Data Index: 1136676 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4983. Min Act: -0.1700

Data Index: 385202 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4983. Min Act: -0.1700

Data Index: 633415 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1075585 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4669. Min Act: -0.1700

Data Index: 218904 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1327184 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4826. Min Act: -0.1700

Data Index: 872330 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4512. Min Act: -0.1700

Data Index: 135097 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1199734 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1001161 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.3728. Min Act: -0.1700

Data Index: 700604 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1113089 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1211889 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1294926 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.4042. Min Act: -0.1700

Data Index: 769062 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 3.6392. Min Range: -3.6392

Max Act: 3.3885. Min Act: -0.1700

Data Index: 291690 (C4 (Web Text))

Max Activating Token Index: 278