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

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

Neuron 1176 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: 5.8968. Min Range: -5.8968

Max Act: 5.8968. Min Act: -0.1700

Data Index: 722151 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.3343. Min Act: -0.1700

Data Index: 70115 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.2718. Min Act: -0.1700

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.2405. Min Act: -0.1700

Data Index: 795024 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1468. Min Act: -0.1700

Data Index: 1352058 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1780. Min Act: -0.1700

Data Index: 763600 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.2093. Min Act: -0.1700

Data Index: 226912 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1155. Min Act: -0.1700

Data Index: 952455 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1155. Min Act: -0.1700

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1780. Min Act: -0.1700

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1468. Min Act: -0.1700

Data Index: 143946 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1468. Min Act: -0.1700

Data Index: 13023 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1155. Min Act: -0.1700

Data Index: 686075 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.0843. Min Act: -0.1700

Data Index: 1239395 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1155. Min Act: -0.1700

Data Index: 1212502 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.1780. Min Act: -0.1700

Data Index: 964357 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.0843. Min Act: -0.1700

Data Index: 1313565 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1159384 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.0843. Min Act: -0.1700

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 5.8968. Min Range: -5.8968

Max Act: 5.0843. Min Act: -0.1700

Data Index: 675552 (C4 (Web Text))

Max Activating Token Index: 522