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

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

Neuron 334 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: 3.4246. Min Range: -3.4246

Max Act: 3.4089. Min Act: -0.1700

Data Index: 320922 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.4246. Min Act: -0.1700

Data Index: 799845 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.4089. Min Act: -0.1700

Data Index: 1325953 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3932. Min Act: -0.1700

Data Index: 302626 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3775. Min Act: -0.1700

Data Index: 486203 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3618. Min Act: -0.1700

Data Index: 632693 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 1326792 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3618. Min Act: -0.1700

Data Index: 235087 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3618. Min Act: -0.1700

Data Index: 1085750 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 159379 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 344678 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 950486 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 441955 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3304. Min Act: -0.1700

Data Index: 232319 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 1008004 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 1182266 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3461. Min Act: -0.1700

Data Index: 882930 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3304. Min Act: -0.1700

Data Index: 873488 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3304. Min Act: -0.1700

Data Index: 613539 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 3.4246. Min Range: -3.4246

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1167361 (C4 (Web Text))

Max Activating Token Index: 818