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

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

Neuron 1095 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: 3.9277. Min Range: -3.9277

Max Act: 3.9277. Min Act: -0.1700

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.8964. Min Act: -0.1700

Data Index: 75195 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.8964. Min Act: -0.1700

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.7713. Min Act: -0.1700

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.8026. Min Act: -0.1700

Data Index: 743143 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6774. Min Act: -0.1700

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.7087. Min Act: -0.1700

Data Index: 1258641 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6774. Min Act: -0.1700

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.7400. Min Act: -0.1700

Data Index: 1226042 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6774. Min Act: -0.1700

Data Index: 924535 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6774. Min Act: -0.1700

Data Index: 199833 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6461. Min Act: -0.1700

Data Index: 243051 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6461. Min Act: -0.1700

Data Index: 965816 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.5835. Min Act: -0.1700

Data Index: 185853 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6461. Min Act: -0.1700

Data Index: 1258644 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6461. Min Act: -0.1700

Data Index: 324868 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.5522. Min Act: -0.1700

Data Index: 275584 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6148. Min Act: -0.1700

Data Index: 1243504 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.5835. Min Act: -0.1700

Data Index: 520880 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.9277. Min Range: -3.9277

Max Act: 3.6148. Min Act: -0.1700

Data Index: 517555 (C4 (Web Text))

Max Activating Token Index: 884