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

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

Neuron 1402 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.9177. Min Act: -0.1700

Data Index: 298128 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8865. Min Act: -0.1700

Data Index: 906119 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8552. Min Act: -0.1700

Data Index: 234160 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.9177. Min Act: -0.1700

Data Index: 146095 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7613. Min Act: -0.1700

Data Index: 211796 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7613. Min Act: -0.1700

Data Index: 1102065 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6988. Min Act: -0.1700

Data Index: 1261239 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6362. Min Act: -0.1700

Data Index: 915875 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6362. Min Act: -0.1700

Data Index: 614962 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6675. Min Act: -0.1700

Data Index: 1085697 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 1349177 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6362. Min Act: -0.1700

Data Index: 85155 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6362. Min Act: -0.1700

Data Index: 415682 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 617839 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1223309 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 123764 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 455516 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 1333721 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6048. Min Act: -0.1700

Data Index: 584890 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.5735. Min Act: -0.1700

Data Index: 317736 (C4 (Web Text))

Max Activating Token Index: 284