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

Dataset: Open Web Text

Neuron 1096 in Layer 0

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: 3.5746. Min Range: -3.5746

Max Act: 3.5746. Min Act: -0.1700

Data Index: 2604703 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.5539. Min Act: -0.1700

Data Index: 405221 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4846. Min Act: -0.1700

Data Index: 5262707 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4887. Min Act: -0.1700

Data Index: 5289844 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4916. Min Act: -0.1700

Data Index: 908847 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4841. Min Act: -0.1700

Data Index: 6632301 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.5005. Min Act: -0.1700

Data Index: 7479081 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4785. Min Act: -0.1700

Data Index: 2373569 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4864. Min Act: -0.1700

Data Index: 1352023 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4457. Min Act: -0.1700

Data Index: 4634898 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4413. Min Act: -0.1700

Data Index: 5032059 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4570. Min Act: -0.1700

Data Index: 2719307 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4571. Min Act: -0.1700

Data Index: 245552 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4693. Min Act: -0.1700

Data Index: 8220568 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4512. Min Act: -0.1700

Data Index: 7784071 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4648. Min Act: -0.1700

Data Index: 5456624 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4546. Min Act: -0.1700

Data Index: 5179891 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4189. Min Act: -0.1700

Data Index: 4490238 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4271. Min Act: -0.1700

Data Index: 4528943 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.5746. Min Range: -3.5746

Max Act: 3.4185. Min Act: -0.1700

Data Index: 882163 (Open Web Text)

Max Activating Token Index: 3