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

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

Neuron 1193 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.7043. Min Act: -0.1700

Data Index: 1072561 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.6886. Min Act: -0.1700

Data Index: 647247 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.6886. Min Act: -0.1700

Data Index: 164214 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.6730. Min Act: -0.1700

Data Index: 1604528 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.6417. Min Act: -0.1700

Data Index: 1037894 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.6104. Min Act: -0.1700

Data Index: 41917 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5791. Min Act: -0.1700

Data Index: 590396 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5947. Min Act: -0.1700

Data Index: 1061929 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5947. Min Act: -0.1700

Data Index: 1442352 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5947. Min Act: -0.1700

Data Index: 1268587 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5791. Min Act: -0.1700

Data Index: 1583589 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5321. Min Act: -0.1700

Data Index: 232469 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5321. Min Act: -0.1700

Data Index: 81605 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5321. Min Act: -0.1700

Data Index: 1023763 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5477. Min Act: -0.1700

Data Index: 26578 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5477. Min Act: -0.1700

Data Index: 1343576 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5321. Min Act: -0.1700

Data Index: 429469 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5477. Min Act: -0.1700

Data Index: 603636 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5164. Min Act: -0.1700

Data Index: 314229 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.7043. Min Range: -3.7043

Max Act: 3.5321. Min Act: -0.1700

Data Index: 751110 (C4 (Web Text))

Max Activating Token Index: 1020