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

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

Neuron 426 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1325. Min Act: -0.1700

Data Index: 901866 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 626218 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1337877 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1345885 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 950405 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 121489 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1010. Min Act: -0.1700

Data Index: 978648 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0852. Min Act: -0.1700

Data Index: 320721 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0695. Min Act: -0.1700

Data Index: 146731 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0695. Min Act: -0.1700

Data Index: 791092 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0852. Min Act: -0.1700

Data Index: 309859 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0852. Min Act: -0.1700

Data Index: 649671 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0695. Min Act: -0.1700

Data Index: 752223 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0537. Min Act: -0.1700

Data Index: 830003 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0537. Min Act: -0.1700

Data Index: 1195644 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0537. Min Act: -0.1700

Data Index: 1124392 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0695. Min Act: -0.1700

Data Index: 1094537 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0537. Min Act: -0.1700

Data Index: 120980 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0695. Min Act: -0.1700

Data Index: 158950 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0537. Min Act: -0.1700

Data Index: 1014625 (C4 (Web Text))

Max Activating Token Index: 795