Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2950. Min Act: -0.1700

Data Index: 166043 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1069583 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1235667 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2321. Min Act: -0.1700

Data Index: 7541 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1273094 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2007. Min Act: -0.1700

Data Index: 93046 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1535. Min Act: -0.1700

Data Index: 606 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1692. Min Act: -0.1700

Data Index: 118172 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1850. Min Act: -0.1700

Data Index: 572752 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1850. Min Act: -0.1700

Data Index: 639417 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1692. Min Act: -0.1700

Data Index: 45088 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1535. Min Act: -0.1700

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1220. Min Act: -0.1700

Data Index: 638904 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1377. Min Act: -0.1700

Data Index: 409954 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1377. Min Act: -0.1700

Data Index: 1336139 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1692. Min Act: -0.1700

Data Index: 769341 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 263843 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1377. Min Act: -0.1700

Data Index: 269971 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0904. Min Act: -0.1700

Data Index: 643879 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0904. Min Act: -0.1700

Data Index: 718086 (C4 (Web Text))

Max Activating Token Index: 522