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

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

Neuron 1976 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.5845. Min Act: -0.1700

Data Index: 875405 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.5220. Min Act: -0.1700

Data Index: 1033377 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.4283. Min Act: -0.1700

Data Index: 286456 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.3970. Min Act: -0.1700

Data Index: 160751 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.2408. Min Act: -0.1700

Data Index: 434116 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.2095. Min Act: -0.1700

Data Index: 798696 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1783. Min Act: -0.1700

Data Index: 521262 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.2408. Min Act: -0.1700

Data Index: 859052 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1783. Min Act: -0.1700

Data Index: 1094951 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1783. Min Act: -0.1700

Data Index: 1236882 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1470. Min Act: -0.1700

Data Index: 587861 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1158. Min Act: -0.1700

Data Index: 343921 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0845. Min Act: -0.1700

Data Index: 471221 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1158. Min Act: -0.1700

Data Index: 1051668 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0533. Min Act: -0.1700

Data Index: 982864 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0845. Min Act: -0.1700

Data Index: 590582 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0533. Min Act: -0.1700

Data Index: 315265 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1132285 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.1158. Min Act: -0.1700

Data Index: 680163 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 5.5845. Min Range: -5.5845

Max Act: 5.0533. Min Act: -0.1700

Data Index: 967907 (C4 (Web Text))

Max Activating Token Index: 976