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

Dataset: Open Web Text

Neuron 1509 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: 0.8680. Min Range: -0.8680

Max Act: 0.8680. Min Act: -0.1700

Data Index: 4401596 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8608. Min Act: -0.1700

Data Index: 5329337 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8580. Min Act: -0.1700

Data Index: 2298693 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8492. Min Act: -0.1700

Data Index: 5814827 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8528. Min Act: -0.1700

Data Index: 2930444 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8412. Min Act: -0.1700

Data Index: 375603 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8415. Min Act: -0.1700

Data Index: 3068881 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8394. Min Act: -0.1700

Data Index: 8258318 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8364. Min Act: -0.1700

Data Index: 4062640 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8348. Min Act: -0.1700

Data Index: 6529533 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8308. Min Act: -0.1700

Data Index: 4579165 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8292. Min Act: -0.1700

Data Index: 1335 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8336. Min Act: -0.1700

Data Index: 1403617 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8287. Min Act: -0.1700

Data Index: 4294183 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8338. Min Act: -0.1700

Data Index: 1613033 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8215. Min Act: -0.1700

Data Index: 3180635 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8162. Min Act: -0.1700

Data Index: 4977256 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8268. Min Act: -0.1700

Data Index: 77942 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8320. Min Act: -0.1700

Data Index: 401457 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8252. Min Act: -0.1700

Data Index: 4577987 (Open Web Text)

Max Activating Token Index: 38