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

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

Neuron 1910 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: 3.3070. Min Range: -3.3070

Max Act: 3.3070. Min Act: -0.1700

Data Index: 146608 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1327404 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1340. Min Act: -0.1700

Data Index: 354428 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1498. Min Act: -0.1700

Data Index: 703640 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1655. Min Act: -0.1700

Data Index: 27170 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0709. Min Act: -0.1700

Data Index: 1305948 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1340. Min Act: -0.1700

Data Index: 667806 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1182. Min Act: -0.1700

Data Index: 493623 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1182. Min Act: -0.1700

Data Index: 876094 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1000244 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0867. Min Act: -0.1700

Data Index: 1103633 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1182. Min Act: -0.1700

Data Index: 612941 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0709. Min Act: -0.1700

Data Index: 163843 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1182. Min Act: -0.1700

Data Index: 496594 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.1182. Min Act: -0.1700

Data Index: 56150 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0394. Min Act: -0.1700

Data Index: 121498 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0867. Min Act: -0.1700

Data Index: 338355 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0867. Min Act: -0.1700

Data Index: 1310865 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0867. Min Act: -0.1700

Data Index: 969511 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.3070. Min Range: -3.3070

Max Act: 3.0709. Min Act: -0.1700

Data Index: 1275987 (C4 (Web Text))

Max Activating Token Index: 492