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

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

Neuron 103 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: 3.5123. Min Range: -3.5123

Max Act: 3.5123. Min Act: -0.1700

Data Index: 631582 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.5123. Min Act: -0.1700

Data Index: 254658 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4809. Min Act: -0.1700

Data Index: 114704 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4966. Min Act: -0.1700

Data Index: 879852 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 1312578 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4966. Min Act: -0.1700

Data Index: 1088019 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4809. Min Act: -0.1700

Data Index: 980572 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 1095224 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 198785 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 804412 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4809. Min Act: -0.1700

Data Index: 391515 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 1114468 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 560103 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4496. Min Act: -0.1700

Data Index: 1102696 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4496. Min Act: -0.1700

Data Index: 1159808 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4496. Min Act: -0.1700

Data Index: 164690 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4653. Min Act: -0.1700

Data Index: 1095755 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4496. Min Act: -0.1700

Data Index: 454448 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4496. Min Act: -0.1700

Data Index: 582065 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 3.5123. Min Range: -3.5123

Max Act: 3.4339. Min Act: -0.1700

Data Index: 43480 (C4 (Web Text))

Max Activating Token Index: 285