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

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

Neuron 515 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.3488. Min Act: -0.1700

Data Index: 800090 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.2231. Min Act: -0.1700

Data Index: 169676 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.1917. Min Act: -0.1700

Data Index: 459304 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.1602. Min Act: -0.1700

Data Index: 879440 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.1602. Min Act: -0.1700

Data Index: 213887 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.1287. Min Act: -0.1700

Data Index: 140046 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.1287. Min Act: -0.1700

Data Index: 399695 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9866. Min Act: -0.1700

Data Index: 1027365 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.0024. Min Act: -0.1700

Data Index: 439417 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 3.3488. Min Range: -3.3488

Max Act: 3.0340. Min Act: -0.1700

Data Index: 693340 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9866. Min Act: -0.1700

Data Index: 68861 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9866. Min Act: -0.1700

Data Index: 18197 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9550. Min Act: -0.1700

Data Index: 1349830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9391. Min Act: -0.1700

Data Index: 1098799 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.9074. Min Act: -0.1700

Data Index: 582632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.8598. Min Act: -0.1700

Data Index: 958416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.8598. Min Act: -0.1700

Data Index: 1080511 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.8757. Min Act: -0.1700

Data Index: 9473 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.8598. Min Act: -0.1700

Data Index: 613330 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.3488. Min Range: -3.3488

Max Act: 2.8598. Min Act: -0.1700

Data Index: 371269 (C4 (Web Text))

Max Activating Token Index: 56