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

Dataset: Open Web Text

Neuron 1697 in Layer 1

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: 4.2486. Min Range: -4.2486

Max Act: 4.2486. Min Act: -0.1700

Data Index: 6862133 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.1067. Min Act: -0.1700

Data Index: 4321283 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.1277. Min Act: -0.1700

Data Index: 5710388 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.1246. Min Act: -0.1700

Data Index: 2941839 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.1164. Min Act: -0.1700

Data Index: 8168014 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0754. Min Act: -0.1700

Data Index: 217859 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0810. Min Act: -0.1700

Data Index: 2327465 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0578. Min Act: -0.1700

Data Index: 4741929 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0499. Min Act: -0.1700

Data Index: 503961 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0442. Min Act: -0.1700

Data Index: 3956712 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0444. Min Act: -0.1700

Data Index: 295111 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0517. Min Act: -0.1700

Data Index: 8166661 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0695. Min Act: -0.1700

Data Index: 7332702 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0449. Min Act: -0.1700

Data Index: 2333326 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0526. Min Act: -0.1700

Data Index: 5553942 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0463. Min Act: -0.1700

Data Index: 2020652 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0130. Min Act: -0.1700

Data Index: 1733015 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0257. Min Act: -0.1700

Data Index: 3109279 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0255. Min Act: -0.1700

Data Index: 3307029 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.2486. Min Range: -4.2486

Max Act: 4.0314. Min Act: -0.1700

Data Index: 4475085 (Open Web Text)

Max Activating Token Index: 228