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

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

Neuron 2030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.3214. Min Act: -0.1700

Data Index: 875870 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1033263 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.3214. Min Act: -0.1700

Data Index: 179377 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2899. Min Act: -0.1700

Data Index: 1223074 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2899. Min Act: -0.1700

Data Index: 83328 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2899. Min Act: -0.1700

Data Index: 256819 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2585. Min Act: -0.1700

Data Index: 168881 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2271. Min Act: -0.1700

Data Index: 80809 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2428. Min Act: -0.1700

Data Index: 709162 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2428. Min Act: -0.1700

Data Index: 595098 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2428. Min Act: -0.1700

Data Index: 1308298 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2585. Min Act: -0.1700

Data Index: 777709 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2114. Min Act: -0.1700

Data Index: 505128 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2271. Min Act: -0.1700

Data Index: 274925 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.1956. Min Act: -0.1700

Data Index: 1204522 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2114. Min Act: -0.1700

Data Index: 784621 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.1956. Min Act: -0.1700

Data Index: 111043 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2114. Min Act: -0.1700

Data Index: 194158 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2114. Min Act: -0.1700

Data Index: 27860 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 3.3214. Min Range: -3.3214

Max Act: 3.2114. Min Act: -0.1700

Data Index: 230941 (C4 (Web Text))

Max Activating Token Index: 807