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

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

Neuron 26 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6799. Min Act: -0.1700

Data Index: 713008 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6799. Min Act: -0.1700

Data Index: 1113083 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6329. Min Act: -0.1700

Data Index: 501360 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6329. Min Act: -0.1700

Data Index: 106170 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6329. Min Act: -0.1700

Data Index: 203674 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5546. Min Act: -0.1700

Data Index: 888723 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6173. Min Act: -0.1700

Data Index: 1093917 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.6016. Min Act: -0.1700

Data Index: 415648 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5390. Min Act: -0.1700

Data Index: 141011 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5859. Min Act: -0.1700

Data Index: 500984 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5390. Min Act: -0.1700

Data Index: 703632 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5859. Min Act: -0.1700

Data Index: 391025 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5859. Min Act: -0.1700

Data Index: 115312 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5703. Min Act: -0.1700

Data Index: 654249 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5233. Min Act: -0.1700

Data Index: 4232 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5546. Min Act: -0.1699

Data Index: 330 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1105485 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5546. Min Act: -0.1700

Data Index: 999855 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5390. Min Act: -0.1700

Data Index: 121499 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.6799. Min Range: -3.6799

Max Act: 3.5390. Min Act: -0.1700

Data Index: 1133582 (C4 (Web Text))

Max Activating Token Index: 930