Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1322 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.8133. Min Act: -0.1700

Data Index: 1114061 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5633. Min Act: -0.1700

Data Index: 423578 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5320. Min Act: -0.1700

Data Index: 248731 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5008. Min Act: -0.1700

Data Index: 646434 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4070. Min Act: -0.1700

Data Index: 878219 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4383. Min Act: -0.1700

Data Index: 526385 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4070. Min Act: -0.1700

Data Index: 791903 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3914. Min Act: -0.1700

Data Index: 161788 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4226. Min Act: -0.1700

Data Index: 2596 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3914. Min Act: -0.1700

Data Index: 322379 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4226. Min Act: -0.1700

Data Index: 921151 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.4070. Min Act: -0.1700

Data Index: 119206 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3914. Min Act: -0.1700

Data Index: 1584 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3601. Min Act: -0.1700

Data Index: 1172598 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3601. Min Act: -0.1700

Data Index: 1003176 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3601. Min Act: -0.1700

Data Index: 223077 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3758. Min Act: -0.1700

Data Index: 1313685 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3445. Min Act: -0.1700

Data Index: 789457 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3289. Min Act: -0.1700

Data Index: 164499 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.3289. Min Act: -0.1700

Data Index: 1250021 (C4 (Web Text))

Max Activating Token Index: 798