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

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

Neuron 887 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.2239. Min Act: -0.1700

Data Index: 665943 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.2082. Min Act: -0.1700

Data Index: 185416 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.2082. Min Act: -0.1700

Data Index: 445876 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1214695 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1610. Min Act: -0.1700

Data Index: 202624 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1335537 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1452. Min Act: -0.1700

Data Index: 904909 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1452. Min Act: -0.1700

Data Index: 831401 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1166748 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1045661 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1295. Min Act: -0.1700

Data Index: 534864 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.0979. Min Act: -0.1700

Data Index: 563549 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 469480 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1160619 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 1016730 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 284083 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.1137. Min Act: -0.1700

Data Index: 500992 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.0979. Min Act: -0.1700

Data Index: 600968 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.0979. Min Act: -0.1700

Data Index: 153440 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.0979. Min Act: -0.1700

Data Index: 653502 (C4 (Web Text))

Max Activating Token Index: 141