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

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

Neuron 1577 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: 5.3464. Min Range: -5.3464

Max Act: 5.3464. Min Act: -0.1700

Data Index: 918729 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.3151. Min Act: -0.1700

Data Index: 446626 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2839. Min Act: -0.1700

Data Index: 125803 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1901. Min Act: -0.1700

Data Index: 141264 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1589. Min Act: -0.1700

Data Index: 1168525 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 250967 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.2526. Min Act: -0.1700

Data Index: 935126 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1276. Min Act: -0.1700

Data Index: 407920 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0964. Min Act: -0.1700

Data Index: 243129 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0964. Min Act: -0.1700

Data Index: 921219 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0964. Min Act: -0.1700

Data Index: 920775 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.1589. Min Act: -0.1700

Data Index: 541179 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 295204 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 914735 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 1118043 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0964. Min Act: -0.1700

Data Index: 647776 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 792212 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 5.3464. Min Range: -5.3464

Max Act: 4.9089. Min Act: -0.1700

Data Index: 996526 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0964. Min Act: -0.1700

Data Index: 1007090 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 5.3464. Min Range: -5.3464

Max Act: 5.0651. Min Act: -0.1700

Data Index: 129584 (C4 (Web Text))

Max Activating Token Index: 165