Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1422 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.7955. Min Act: -0.1700

Data Index: 1005704 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.7414. Min Act: -0.1700

Data Index: 1208495 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.7276. Min Act: -0.1700

Data Index: 747314 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.7432. Min Act: -0.1700

Data Index: 21741 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.7424. Min Act: -0.1700

Data Index: 737792 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6884. Min Act: -0.1700

Data Index: 167978 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6578. Min Act: -0.1700

Data Index: 486551 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6439. Min Act: -0.1700

Data Index: 688279 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6116. Min Act: -0.1700

Data Index: 176673 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6409. Min Act: -0.1700

Data Index: 74889 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5830. Min Act: -0.1700

Data Index: 211262 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5468. Min Act: -0.1700

Data Index: 100747 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5579. Min Act: -0.1700

Data Index: 96652 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1185265 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.6077. Min Act: -0.1700

Data Index: 56585 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5618. Min Act: -0.1700

Data Index: 809081 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5341. Min Act: -0.1700

Data Index: 870972 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5519. Min Act: -0.1700

Data Index: 954574 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1254879 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 3.7955. Min Range: -3.7955

Max Act: 3.4913. Min Act: -0.1700

Data Index: 1167778 (C4 (Web Text))

Max Activating Token Index: 22