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

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

Neuron 1144 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3945. Min Act: -0.1700

Data Index: 861384 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3788. Min Act: -0.1700

Data Index: 324927 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3317. Min Act: -0.1700

Data Index: 90783 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3160. Min Act: -0.1700

Data Index: 436447 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3003. Min Act: -0.1700

Data Index: 549800 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3160. Min Act: -0.1700

Data Index: 226300 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3003. Min Act: -0.1700

Data Index: 160908 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.3003. Min Act: -0.1700

Data Index: 122290 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1251808 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 105141 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 477842 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2689. Min Act: -0.1700

Data Index: 1290333 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 400614 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1091632 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 528775 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1340401 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 931060 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2846. Min Act: -0.1700

Data Index: 448468 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1160306 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.3945. Min Range: -3.3945

Max Act: 3.2689. Min Act: -0.1700

Data Index: 1592130 (Python Code)

Max Activating Token Index: 38