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

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

Neuron 362 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: 5.4591. Min Range: -5.4591

Max Act: 5.4591. Min Act: -0.1700

Data Index: 812290 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.4591. Min Act: -0.1700

Data Index: 622369 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.3341. Min Act: -0.1700

Data Index: 1001937 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.2716. Min Act: -0.1700

Data Index: 852690 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.2091. Min Act: -0.1700

Data Index: 1051773 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1466. Min Act: -0.1700

Data Index: 1095448 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1778. Min Act: -0.1700

Data Index: 161349 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1778. Min Act: -0.1700

Data Index: 1271906 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1466. Min Act: -0.1700

Data Index: 646816 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1466. Min Act: -0.1700

Data Index: 635975 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1153. Min Act: -0.1700

Data Index: 1210451 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 1158475 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 928091 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 1303365 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 907096 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 1067160 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 1238429 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0841. Min Act: -0.1700

Data Index: 451094 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.1153. Min Act: -0.1700

Data Index: 225461 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 5.4591. Min Range: -5.4591

Max Act: 5.0528. Min Act: -0.1700

Data Index: 421741 (C4 (Web Text))

Max Activating Token Index: 647