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

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

Neuron 140 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: 3.3592. Min Range: -3.3592

Max Act: 3.3592. Min Act: -0.1700

Data Index: 947987 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.3278. Min Act: -0.1700

Data Index: 359914 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.3278. Min Act: -0.1700

Data Index: 443108 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2964. Min Act: -0.1700

Data Index: 1285041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2964. Min Act: -0.1700

Data Index: 323069 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2964. Min Act: -0.1700

Data Index: 49523 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2650. Min Act: -0.1700

Data Index: 128085 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2964. Min Act: -0.1700

Data Index: 293151 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.3278. Min Act: -0.1700

Data Index: 1119320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2650. Min Act: -0.1700

Data Index: 442349 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2650. Min Act: -0.1700

Data Index: 986559 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2650. Min Act: -0.1700

Data Index: 1102405 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2964. Min Act: -0.1700

Data Index: 807569 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2021. Min Act: -0.1700

Data Index: 690001 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2021. Min Act: -0.1700

Data Index: 840392 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2335. Min Act: -0.1700

Data Index: 524444 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2021. Min Act: -0.1700

Data Index: 693117 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2335. Min Act: -0.1700

Data Index: 723175 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2650. Min Act: -0.1700

Data Index: 639586 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2335. Min Act: -0.1700

Data Index: 584917 (C4 (Web Text))

Max Activating Token Index: 942