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

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

Neuron 26 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: 4.5835. Min Range: -4.5835

Max Act: 4.5522. Min Act: -0.1700

Data Index: 371433 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.4897. Min Act: -0.1700

Data Index: 1060179 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.5835. Min Act: -0.1700

Data Index: 490623 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 221517 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3960. Min Act: -0.1700

Data Index: 908784 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 287504 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 399959 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 1337347 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 147458 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 402638 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 218843 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 159176 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3960. Min Act: -0.1700

Data Index: 476556 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 453051 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 68799 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3335. Min Act: -0.1700

Data Index: 151157 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 1080930 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3022. Min Act: -0.1700

Data Index: 616353 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3022. Min Act: -0.1700

Data Index: 993435 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 742749 (C4 (Web Text))

Max Activating Token Index: 23