Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1584 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.3827. Min Act: -0.1700

Data Index: 1547410 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2160. Min Act: -0.1700

Data Index: 1596053 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.2012. Min Act: -0.1700

Data Index: 247515 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1995. Min Act: -0.1700

Data Index: 153114 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1692. Min Act: -0.1700

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1539. Min Act: -0.1700

Data Index: 256227 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1519. Min Act: -0.1700

Data Index: 1505859 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1311. Min Act: -0.1700

Data Index: 435680 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1386. Min Act: -0.1700

Data Index: 573784 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1076. Min Act: -0.1699

Data Index: 26796 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1349. Min Act: -0.1700

Data Index: 207943 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1106. Min Act: -0.1700

Data Index: 186637 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0990. Min Act: -0.1700

Data Index: 212573 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1047. Min Act: -0.1700

Data Index: 1261730 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.1021. Min Act: -0.1700

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0824. Min Act: -0.1700

Data Index: 1644383 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0818. Min Act: -0.1700

Data Index: 1484271 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0888. Min Act: -0.1700

Data Index: 724055 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0978. Min Act: -0.1700

Data Index: 518858 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 3.3827. Min Range: -3.3827

Max Act: 3.0879. Min Act: -0.1700

Data Index: 597949 (C4 (Web Text))

Max Activating Token Index: 988