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

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

Neuron 1364 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.6865. Min Act: -0.1700

Data Index: 807195 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.4053. Min Act: -0.1700

Data Index: 1185735 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.3740. Min Act: -0.1700

Data Index: 412404 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.4053. Min Act: -0.1700

Data Index: 469659 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.3428. Min Act: -0.1700

Data Index: 137976 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2803. Min Act: -0.1700

Data Index: 684518 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2803. Min Act: -0.1700

Data Index: 253178 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2178. Min Act: -0.1700

Data Index: 506665 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2178. Min Act: -0.1700

Data Index: 876040 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1865. Min Act: -0.1700

Data Index: 950267 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1553. Min Act: -0.1700

Data Index: 975658 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1553. Min Act: -0.1700

Data Index: 20136 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2178. Min Act: -0.1700

Data Index: 1051352 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1865. Min Act: -0.1700

Data Index: 973976 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.2178. Min Act: -0.1700

Data Index: 976832 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1553. Min Act: -0.1700

Data Index: 1251135 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1553. Min Act: -0.1700

Data Index: 735498 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1240. Min Act: -0.1700

Data Index: 292530 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1240. Min Act: -0.1700

Data Index: 196731 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 5.6865. Min Range: -5.6865

Max Act: 5.1240. Min Act: -0.1700

Data Index: 858455 (C4 (Web Text))

Max Activating Token Index: 911