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

Dataset: Open Web Text

Neuron 1394 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: 4.5765. Min Range: -4.5765

Max Act: 4.5765. Min Act: -0.1700

Data Index: 3786939 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.5242. Min Act: -0.1700

Data Index: 6084226 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.5375. Min Act: -0.1700

Data Index: 1442200 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4949. Min Act: -0.1700

Data Index: 6684129 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.5348. Min Act: -0.1700

Data Index: 6391003 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.5207. Min Act: -0.1700

Data Index: 8138687 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4619. Min Act: -0.1700

Data Index: 2291245 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4949. Min Act: -0.1700

Data Index: 1918816 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.5001. Min Act: -0.1700

Data Index: 8184119 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4490. Min Act: -0.1700

Data Index: 4785398 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4435. Min Act: -0.1700

Data Index: 5327100 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4527. Min Act: -0.1700

Data Index: 5700593 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4426. Min Act: -0.1700

Data Index: 7774395 (Open Web Text)

Max Activating Token Index: 578

Text #13

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4508. Min Act: -0.1700

Data Index: 7322337 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4179. Min Act: -0.1700

Data Index: 2682938 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4264. Min Act: -0.1700

Data Index: 4359698 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4160. Min Act: -0.1700

Data Index: 4372042 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4198. Min Act: -0.1700

Data Index: 1319685 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4183. Min Act: -0.1700

Data Index: 1704326 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 4.5765. Min Range: -4.5765

Max Act: 4.4182. Min Act: -0.1700

Data Index: 3150546 (Open Web Text)

Max Activating Token Index: 462