Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5988. Min Act: -0.1700

Data Index: 2629759 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5822. Min Act: -0.1700

Data Index: 6313206 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5782. Min Act: -0.1700

Data Index: 3679199 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5263. Min Act: -0.1700

Data Index: 4169410 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4884. Min Act: -0.1700

Data Index: 5230437 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4868. Min Act: -0.1700

Data Index: 752424 (Open Web Text)

Max Activating Token Index: 1021

Text #6

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4650. Min Act: -0.1700

Data Index: 720619 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4300. Min Act: -0.1700

Data Index: 5117462 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4027. Min Act: -0.1700

Data Index: 8027608 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4067. Min Act: -0.1700

Data Index: 2168347 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4036. Min Act: -0.1700

Data Index: 7741788 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3929. Min Act: -0.1700

Data Index: 6571853 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3910. Min Act: -0.1700

Data Index: 4818728 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4075. Min Act: -0.1700

Data Index: 3352837 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3891. Min Act: -0.1700

Data Index: 1752498 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3904. Min Act: -0.1700

Data Index: 386195 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3782. Min Act: -0.1700

Data Index: 6291870 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3887. Min Act: -0.1700

Data Index: 7002813 (Open Web Text)

Max Activating Token Index: 497

Text #18

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3819. Min Act: -0.1700

Data Index: 6926763 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3584. Min Act: -0.1700

Data Index: 2317738 (Open Web Text)

Max Activating Token Index: 334