Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 868 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.4147. Min Act: -0.1700

Data Index: 198236 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.3835. Min Act: -0.1700

Data Index: 1114956 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.3522. Min Act: -0.1700

Data Index: 403880 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.3522. Min Act: -0.1700

Data Index: 592003 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.3522. Min Act: -0.1700

Data Index: 1161778 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.3522. Min Act: -0.1700

Data Index: 959216 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.2272. Min Act: -0.1700

Data Index: 231906 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.1960. Min Act: -0.1700

Data Index: 153317 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.1647. Min Act: -0.1700

Data Index: 463400 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.1647. Min Act: -0.1700

Data Index: 407369 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.1022. Min Act: -0.1700

Data Index: 321374 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 147921 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0085. Min Act: -0.1700

Data Index: 742679 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0397. Min Act: -0.1700

Data Index: 1188832 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 1304729 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 1319096 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 699760 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0397. Min Act: -0.1700

Data Index: 699449 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 583663 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 5.4147. Min Range: -5.4147

Max Act: 5.0710. Min Act: -0.1700

Data Index: 444766 (C4 (Web Text))

Max Activating Token Index: 566