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

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

Neuron 932 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: 5.8946. Min Range: -5.8946

Max Act: 5.8946. Min Act: -0.1700

Data Index: 132484 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.6446. Min Act: -0.1700

Data Index: 714707 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.4258. Min Act: -0.1700

Data Index: 1039713 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.4883. Min Act: -0.1700

Data Index: 973942 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3946. Min Act: -0.1700

Data Index: 847271 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3946. Min Act: -0.1700

Data Index: 100395 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.4258. Min Act: -0.1700

Data Index: 695190 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.4571. Min Act: -0.1700

Data Index: 74407 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3633. Min Act: -0.1700

Data Index: 1158742 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3946. Min Act: -0.1700

Data Index: 831345 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2071. Min Act: -0.1700

Data Index: 698934 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3321. Min Act: -0.1700

Data Index: 727481 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2696. Min Act: -0.1700

Data Index: 1096368 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2539. Min Act: -0.1700

Data Index: 111009 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2852. Min Act: -0.1700

Data Index: 1117394 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.3946. Min Act: -0.1700

Data Index: 700952 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2227. Min Act: -0.1700

Data Index: 984029 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.0508. Min Act: -0.1700

Data Index: 92547 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2539. Min Act: -0.1700

Data Index: 821508 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 5.8946. Min Range: -5.8946

Max Act: 5.2383. Min Act: -0.1700

Data Index: 228013 (C4 (Web Text))

Max Activating Token Index: 564