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

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

Neuron 988 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: 7.1352. Min Range: -7.1352

Max Act: 7.1352. Min Act: -0.1700

Data Index: 288108 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.7915. Min Act: -0.1700

Data Index: 1211731 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.6665. Min Act: -0.1700

Data Index: 112736 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.6040. Min Act: -0.1700

Data Index: 916342 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.4165. Min Act: -0.1700

Data Index: 1272277 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.3540. Min Act: -0.1700

Data Index: 745037 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.3227. Min Act: -0.1700

Data Index: 446651 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.2915. Min Act: -0.1700

Data Index: 502773 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.2602. Min Act: -0.1700

Data Index: 350340 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.3227. Min Act: -0.1700

Data Index: 1326019 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.1665. Min Act: -0.1700

Data Index: 984004 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.2602. Min Act: -0.1700

Data Index: 525020 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.2290. Min Act: -0.1700

Data Index: 1319600 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.1977. Min Act: -0.1700

Data Index: 90998 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.1352. Min Act: -0.1700

Data Index: 551547 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.2602. Min Act: -0.1700

Data Index: 1090913 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.1352. Min Act: -0.1700

Data Index: 134378 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.1665. Min Act: -0.1700

Data Index: 1209236 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.0415. Min Act: -0.1700

Data Index: 756976 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 7.1352. Min Range: -7.1352

Max Act: 6.0102. Min Act: -0.1700

Data Index: 479442 (C4 (Web Text))

Max Activating Token Index: 996