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

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

Neuron 1808 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.6838. Min Act: -0.1700

Data Index: 593825 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5585. Min Act: -0.1700

Data Index: 1003005 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5272. Min Act: -0.1700

Data Index: 1209363 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5272. Min Act: -0.1700

Data Index: 222852 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5272. Min Act: -0.1700

Data Index: 205688 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5115. Min Act: -0.1700

Data Index: 485456 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4802. Min Act: -0.1700

Data Index: 743273 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4645. Min Act: -0.1700

Data Index: 58554 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4489. Min Act: -0.1700

Data Index: 973434 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4489. Min Act: -0.1700

Data Index: 1340193 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4332. Min Act: -0.1700

Data Index: 901084 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3861. Min Act: -0.1700

Data Index: 727935 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3861. Min Act: -0.1700

Data Index: 950978 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3861. Min Act: -0.1700

Data Index: 457646 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1250384 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3861. Min Act: -0.1700

Data Index: 1020269 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3704. Min Act: -0.1700

Data Index: 945138 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3704. Min Act: -0.1700

Data Index: 27239 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1166767 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1245917 (C4 (Web Text))

Max Activating Token Index: 297