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

Dataset: Open Web Text

Neuron 2597 in Layer 0

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: 3.6636. Min Range: -3.6636

Max Act: 3.6636. Min Act: -0.1700

Data Index: 6577451 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4532. Min Act: -0.1700

Data Index: 2514228 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2993. Min Act: -0.1700

Data Index: 8023358 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3208. Min Act: -0.1700

Data Index: 8525322 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2975. Min Act: -0.1700

Data Index: 4390535 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2703. Min Act: -0.1700

Data Index: 5153709 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2257. Min Act: -0.1700

Data Index: 5448418 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2181. Min Act: -0.1700

Data Index: 7511430 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1420873 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1950. Min Act: -0.1700

Data Index: 8655887 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1998. Min Act: -0.1700

Data Index: 2479876 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1740. Min Act: -0.1700

Data Index: 3434337 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1717. Min Act: -0.1700

Data Index: 518078 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1550. Min Act: -0.1700

Data Index: 5191324 (Open Web Text)

Max Activating Token Index: 891

Text #14

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1637. Min Act: -0.1700

Data Index: 8719395 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1609. Min Act: -0.1700

Data Index: 5974513 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1631. Min Act: -0.1700

Data Index: 690387 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1716. Min Act: -0.1700

Data Index: 8452922 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1430. Min Act: -0.1700

Data Index: 4902648 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.1533. Min Act: -0.1700

Data Index: 7406050 (Open Web Text)

Max Activating Token Index: 5