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

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

Neuron 741 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: 7.4467. Min Range: -7.4467

Max Act: 7.2904. Min Act: -0.1700

Data Index: 624024 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.4467. Min Act: -0.1700

Data Index: 1267649 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.3217. Min Act: -0.1700

Data Index: 1333419 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.4467. Min Act: -0.1700

Data Index: 470200 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.3217. Min Act: -0.1700

Data Index: 422974 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.3529. Min Act: -0.1700

Data Index: 1266690 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1654. Min Act: -0.1700

Data Index: 867072 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.2904. Min Act: -0.1700

Data Index: 1047220 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.2279. Min Act: -0.1700

Data Index: 42360 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.2279. Min Act: -0.1700

Data Index: 656091 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.2279. Min Act: -0.1700

Data Index: 1060329 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.3217. Min Act: -0.1700

Data Index: 854018 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1654. Min Act: -0.1700

Data Index: 579410 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1967. Min Act: -0.1700

Data Index: 20134 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.2592. Min Act: -0.1700

Data Index: 789164 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1654. Min Act: -0.1700

Data Index: 1109638 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1029. Min Act: -0.1700

Data Index: 403856 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1029. Min Act: -0.1700

Data Index: 735732 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1029. Min Act: -0.1700

Data Index: 694936 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 7.4467. Min Range: -7.4467

Max Act: 7.1967. Min Act: -0.1700

Data Index: 180589 (C4 (Web Text))

Max Activating Token Index: 682