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

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

Neuron 2037 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.1605. Min Range: -4.1605

Max Act: 4.1605. Min Act: -0.1700

Data Index: 372900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1605. Min Range: -4.1605

Max Act: 4.1292. Min Act: -0.1700

Data Index: 3328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.1605. Min Range: -4.1605

Max Act: 4.1292. Min Act: -0.1700

Data Index: 490914 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.1605. Min Range: -4.1605

Max Act: 4.0354. Min Act: -0.1700

Data Index: 1182499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.9103. Min Act: -0.1700

Data Index: 663505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.9103. Min Act: -0.1700

Data Index: 1170228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8791. Min Act: -0.1700

Data Index: 311665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8791. Min Act: -0.1700

Data Index: 1084701 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.7539. Min Act: -0.1700

Data Index: 907425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.9103. Min Act: -0.1700

Data Index: 958122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.7852. Min Act: -0.1700

Data Index: 101103 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8165. Min Act: -0.1700

Data Index: 1047607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.7852. Min Act: -0.1700

Data Index: 782624 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8165. Min Act: -0.1700

Data Index: 840346 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8165. Min Act: -0.1700

Data Index: 46462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.7852. Min Act: -0.1700

Data Index: 397729 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8478. Min Act: -0.1700

Data Index: 1163862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8478. Min Act: -0.1700

Data Index: 954745 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.8478. Min Act: -0.1700

Data Index: 314737 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 4.1605. Min Range: -4.1605

Max Act: 3.7852. Min Act: -0.1700

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 423