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

Dataset: Open Web Text

Neuron 1444 in Layer 2

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: 1.7677. Min Range: -1.7677

Max Act: 1.7650. Min Act: -0.1700

Data Index: 4615797 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7677. Min Act: -0.1700

Data Index: 2278492 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7393. Min Act: -0.1700

Data Index: 7625198 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7402. Min Act: -0.1700

Data Index: 5775497 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7402. Min Act: -0.1700

Data Index: 6298025 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7306. Min Act: -0.1700

Data Index: 8525189 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7308. Min Act: -0.1694

Data Index: 2958430 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7255. Min Act: -0.1700

Data Index: 2137715 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7187. Min Act: -0.1700

Data Index: 235835 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7119. Min Act: -0.1699

Data Index: 7284723 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6990. Min Act: -0.1700

Data Index: 6293571 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6972. Min Act: -0.1700

Data Index: 1203721 (Open Web Text)

Max Activating Token Index: 742

Text #12

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6879. Min Act: -0.1700

Data Index: 6480015 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6983. Min Act: -0.1700

Data Index: 4819092 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7041. Min Act: -0.1700

Data Index: 8773216 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.7090. Min Act: -0.1700

Data Index: 7064353 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6824. Min Act: -0.1700

Data Index: 1027131 (Open Web Text)

Max Activating Token Index: 189

Text #17

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6895. Min Act: -0.1700

Data Index: 7817842 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6872. Min Act: -0.1700

Data Index: 4276501 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 1.7677. Min Range: -1.7677

Max Act: 1.6895. Min Act: -0.1700

Data Index: 1405514 (Open Web Text)

Max Activating Token Index: 64