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

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

Neuron 1257 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2555. Min Range: -10.2555

Max Act: 10.2555. Min Act: -0.1700

Data Index: 757607 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 10.2555. Min Range: -10.2555

Max Act: 10.1930. Min Act: -0.1700

Data Index: 774841 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.8805. Min Act: -0.1700

Data Index: 1192648 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.5680. Min Act: -0.1700

Data Index: 198570 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.6305. Min Act: -0.1700

Data Index: 206401 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.6305. Min Act: -0.1700

Data Index: 319155 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3805. Min Act: -0.1700

Data Index: 122488 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.4430. Min Act: -0.1700

Data Index: 1285944 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.5055. Min Act: -0.1700

Data Index: 935021 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.5055. Min Act: -0.1700

Data Index: 713511 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3805. Min Act: -0.1700

Data Index: 146504 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.4430. Min Act: -0.1700

Data Index: 618381 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3180. Min Act: -0.1700

Data Index: 60219 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3180. Min Act: -0.1700

Data Index: 1033014 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.1305. Min Act: -0.1700

Data Index: 732783 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.2555. Min Act: -0.1700

Data Index: 400007 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3180. Min Act: -0.1700

Data Index: 707659 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3180. Min Act: -0.1700

Data Index: 942273 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.2555. Min Act: -0.1700

Data Index: 1120293 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 10.2555. Min Range: -10.2555

Max Act: 9.3180. Min Act: -0.1700

Data Index: 682650 (C4 (Web Text))

Max Activating Token Index: 487