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

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

Neuron 1495 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: 3.6899. Min Range: -3.6899

Max Act: 3.6899. Min Act: -0.1700

Data Index: 186283 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.5647. Min Act: -0.1700

Data Index: 938673 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.3609. Min Act: -0.1700

Data Index: 1156991 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.3295. Min Act: -0.1700

Data Index: 65163 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.3452. Min Act: -0.1700

Data Index: 1232508 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2824. Min Act: -0.1700

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.3295. Min Act: -0.1700

Data Index: 108415 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2981. Min Act: -0.1700

Data Index: 742148 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2667. Min Act: -0.1700

Data Index: 1288660 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2667. Min Act: -0.1700

Data Index: 80270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2824. Min Act: -0.1700

Data Index: 70963 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2353. Min Act: -0.1700

Data Index: 554688 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.1881. Min Act: -0.1700

Data Index: 1150379 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2195. Min Act: -0.1699

Data Index: 927089 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1287059 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2038. Min Act: -0.1700

Data Index: 432380 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1147695 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1070634 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.6899. Min Range: -3.6899

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 45