Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 456 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.4355. Min Act: -0.1700

Data Index: 79106 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.4980. Min Act: -0.1700

Data Index: 990086 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.3730. Min Act: -0.1700

Data Index: 344877 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.2480. Min Act: -0.1700

Data Index: 1359441 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.1855. Min Act: -0.1700

Data Index: 817227 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.1855. Min Act: -0.1700

Data Index: 1136574 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.1230. Min Act: -0.1700

Data Index: 1025110 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.1855. Min Act: -0.1700

Data Index: 557104 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 7.4980. Min Range: -7.4980

Max Act: 7.0605. Min Act: -0.1700

Data Index: 243785 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9980. Min Act: -0.1700

Data Index: 84835 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9980. Min Act: -0.1700

Data Index: 544376 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9980. Min Act: -0.1700

Data Index: 467219 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9980. Min Act: -0.1700

Data Index: 89425 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9980. Min Act: -0.1700

Data Index: 839465 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9355. Min Act: -0.1700

Data Index: 788193 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.8418. Min Act: -0.1700

Data Index: 1002484 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.9043. Min Act: -0.1700

Data Index: 687865 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.8730. Min Act: -0.1700

Data Index: 210001 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.8418. Min Act: -0.1700

Data Index: 333862 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 7.4980. Min Range: -7.4980

Max Act: 6.8418. Min Act: -0.1700

Data Index: 1152386 (C4 (Web Text))

Max Activating Token Index: 155