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

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

Neuron 1453 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1314753 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.5468. Min Act: -0.1700

Data Index: 1143605 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1334037 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.4371. Min Act: -0.1700

Data Index: 197986 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.4215. Min Act: -0.1700

Data Index: 933561 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.4215. Min Act: -0.1700

Data Index: 1025269 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.4058. Min Act: -0.1700

Data Index: 838470 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3744. Min Act: -0.1700

Data Index: 707260 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3744. Min Act: -0.1700

Data Index: 1146929 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3430. Min Act: -0.1700

Data Index: 1248358 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3430. Min Act: -0.1700

Data Index: 532656 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3430. Min Act: -0.1700

Data Index: 375086 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3430. Min Act: -0.1700

Data Index: 776544 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3430. Min Act: -0.1700

Data Index: 383010 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3273. Min Act: -0.1700

Data Index: 321768 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3273. Min Act: -0.1700

Data Index: 1134136 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.3273. Min Act: -0.1700

Data Index: 420999 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.2802. Min Act: -0.1700

Data Index: 128574 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.2802. Min Act: -0.1700

Data Index: 1010709 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.5782. Min Range: -3.5782

Max Act: 3.2959. Min Act: -0.1700

Data Index: 41739 (C4 (Web Text))

Max Activating Token Index: 428