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

Dataset: Open Web Text

Neuron 1791 in Layer 6

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: 4.2183. Min Range: -4.2183

Max Act: 4.2183. Min Act: -0.1700

Data Index: 8225839 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.2183. Min Act: -0.1700

Data Index: 7519853 (Open Web Text)

Max Activating Token Index: 817

Text #2

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.2043. Min Act: -0.1700

Data Index: 7364622 (Open Web Text)

Max Activating Token Index: 457

Text #3

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0203. Min Act: -0.1700

Data Index: 1531941 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0516. Min Act: -0.1700

Data Index: 174112 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0489. Min Act: -0.1700

Data Index: 5419110 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0517. Min Act: -0.1700

Data Index: 2984969 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0375. Min Act: -0.1700

Data Index: 8599708 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0427. Min Act: -0.1700

Data Index: 8769410 (Open Web Text)

Max Activating Token Index: 425

Text #9

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0478. Min Act: -0.1700

Data Index: 312832 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9492. Min Act: -0.1700

Data Index: 6342130 (Open Web Text)

Max Activating Token Index: 758

Text #11

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9934. Min Act: -0.1700

Data Index: 2472971 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9769. Min Act: -0.1700

Data Index: 4741877 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 4.2183. Min Range: -4.2183

Max Act: 4.0144. Min Act: -0.1700

Data Index: 6285302 (Open Web Text)

Max Activating Token Index: 742

Text #14

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9957. Min Act: -0.1700

Data Index: 7299126 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9461. Min Act: -0.1700

Data Index: 7235849 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9975. Min Act: -0.1700

Data Index: 133462 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9901. Min Act: -0.1700

Data Index: 5718010 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9704. Min Act: -0.1700

Data Index: 6798503 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 4.2183. Min Range: -4.2183

Max Act: 3.9684. Min Act: -0.1700

Data Index: 6397470 (Open Web Text)

Max Activating Token Index: 590