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

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

Neuron 123 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: 3.4094. Min Range: -3.4094

Max Act: 3.4094. Min Act: -0.1700

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3780. Min Act: -0.1700

Data Index: 77554 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3780. Min Act: -0.1700

Data Index: 27387 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3780. Min Act: -0.1700

Data Index: 45532 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3624. Min Act: -0.1700

Data Index: 1149747 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3624. Min Act: -0.1700

Data Index: 965896 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 807148 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 1008344 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3467. Min Act: -0.1700

Data Index: 683564 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 1043387 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.2996. Min Act: -0.1700

Data Index: 199074 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3153. Min Act: -0.1700

Data Index: 1180678 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 1151724 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 655742 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 826040 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.2996. Min Act: -0.1700

Data Index: 1311812 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3310. Min Act: -0.1700

Data Index: 1185949 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3153. Min Act: -0.1700

Data Index: 1091188 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3153. Min Act: -0.1700

Data Index: 497742 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.4094. Min Range: -3.4094

Max Act: 3.3153. Min Act: -0.1700

Data Index: 743549 (C4 (Web Text))

Max Activating Token Index: 496