Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1913 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3778. Min Act: -0.1700

Data Index: 504955 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3778. Min Act: -0.1700

Data Index: 248642 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2836. Min Act: -0.1700

Data Index: 495734 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3621. Min Act: -0.1700

Data Index: 612782 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3464. Min Act: -0.1700

Data Index: 1061775 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3307. Min Act: -0.1700

Data Index: 680271 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.3150. Min Act: -0.1700

Data Index: 1188030 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2836. Min Act: -0.1700

Data Index: 644191 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2836. Min Act: -0.1700

Data Index: 152186 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2836. Min Act: -0.1700

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2836. Min Act: -0.1700

Data Index: 1183616 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2679. Min Act: -0.1700

Data Index: 923525 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2522. Min Act: -0.1700

Data Index: 487231 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1078930 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2364. Min Act: -0.1700

Data Index: 212004 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1103447 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2522. Min Act: -0.1700

Data Index: 760838 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1192388 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2522. Min Act: -0.1700

Data Index: 729094 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.3778. Min Range: -3.3778

Max Act: 3.2207. Min Act: -0.1700

Data Index: 727629 (C4 (Web Text))

Max Activating Token Index: 691