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

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

Neuron 1119 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.3588. Min Act: -0.1700

Data Index: 887598 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.3588. Min Act: -0.1700

Data Index: 1268754 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2960. Min Act: -0.1700

Data Index: 1296810 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2803. Min Act: -0.1700

Data Index: 168314 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.3117. Min Act: -0.1700

Data Index: 116783 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2960. Min Act: -0.1700

Data Index: 624122 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.3117. Min Act: -0.1700

Data Index: 427857 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2488. Min Act: -0.1700

Data Index: 517423 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2803. Min Act: -0.1700

Data Index: 750340 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2174. Min Act: -0.1700

Data Index: 1040913 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1859. Min Act: -0.1700

Data Index: 1332053 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1859. Min Act: -0.1700

Data Index: 1216811 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2017. Min Act: -0.1700

Data Index: 811331 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.2017. Min Act: -0.1700

Data Index: 911423 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1859. Min Act: -0.1700

Data Index: 839981 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1859. Min Act: -0.1700

Data Index: 261666 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1702. Min Act: -0.1700

Data Index: 498203 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1545. Min Act: -0.1700

Data Index: 842115 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1229. Min Act: -0.1700

Data Index: 831002 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.3588. Min Range: -3.3588

Max Act: 3.1702. Min Act: -0.1700

Data Index: 168379 (C4 (Web Text))

Max Activating Token Index: 155