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

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

Neuron 131 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: 3.5150. Min Range: -3.5150

Max Act: 3.5150. Min Act: -0.1700

Data Index: 831889 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4837. Min Act: -0.1700

Data Index: 811637 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4837. Min Act: -0.1700

Data Index: 220067 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4680. Min Act: -0.1700

Data Index: 1211170 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4524. Min Act: -0.1700

Data Index: 206806 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4524. Min Act: -0.1700

Data Index: 216958 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4367. Min Act: -0.1700

Data Index: 655801 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4367. Min Act: -0.1700

Data Index: 289487 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4053. Min Act: -0.1700

Data Index: 884595 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3896. Min Act: -0.1700

Data Index: 867921 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4053. Min Act: -0.1700

Data Index: 820416 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3896. Min Act: -0.1700

Data Index: 151381 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.4053. Min Act: -0.1700

Data Index: 1348898 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3269. Min Act: -0.1700

Data Index: 492332 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3740. Min Act: -0.1700

Data Index: 560680 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3426. Min Act: -0.1700

Data Index: 652199 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1312342 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3426. Min Act: -0.1700

Data Index: 708053 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3426. Min Act: -0.1700

Data Index: 355349 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 3.5150. Min Range: -3.5150

Max Act: 3.3112. Min Act: -0.1700

Data Index: 855981 (C4 (Web Text))

Max Activating Token Index: 419