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

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

Neuron 1993 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: 5.6155. Min Range: -5.6155

Max Act: 5.6155. Min Act: -0.1700

Data Index: 20772 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.6155. Min Act: -0.1700

Data Index: 361516 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 1061177 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 100241 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5843. Min Act: -0.1700

Data Index: 1100351 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 176220 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 836823 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 38572 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 806169 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 332389 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 432983 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 531610 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 197339 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 539078 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 244030 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 589714 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4905. Min Act: -0.1700

Data Index: 635403 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 645507 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.5218. Min Act: -0.1700

Data Index: 949704 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 5.6155. Min Range: -5.6155

Max Act: 5.4593. Min Act: -0.1700

Data Index: 1230973 (C4 (Web Text))

Max Activating Token Index: 812