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

Dataset: Open Web Text

Neuron 1496 in Layer 3

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: 1.8621. Min Range: -1.8621

Max Act: 1.8531. Min Act: -0.1700

Data Index: 827913 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8528. Min Act: -0.1700

Data Index: 426437 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8553. Min Act: -0.1700

Data Index: 8282396 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8433. Min Act: -0.1700

Data Index: 1215140 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8621. Min Act: -0.1700

Data Index: 8602492 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8487. Min Act: -0.1700

Data Index: 4768728 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8208. Min Act: -0.1700

Data Index: 1950017 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8280. Min Act: -0.1700

Data Index: 8553639 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8221. Min Act: -0.1700

Data Index: 2611611 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8284. Min Act: -0.1700

Data Index: 7729581 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8159. Min Act: -0.1700

Data Index: 7386690 (Open Web Text)

Max Activating Token Index: 721

Text #11

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8160. Min Act: -0.1700

Data Index: 3017332 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8332. Min Act: -0.1700

Data Index: 2219366 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8188. Min Act: -0.1700

Data Index: 1480135 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8108. Min Act: -0.1700

Data Index: 2923658 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8062. Min Act: -0.1700

Data Index: 8388218 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8084. Min Act: -0.1700

Data Index: 5657047 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8240. Min Act: -0.1700

Data Index: 7079867 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.8238. Min Act: -0.1700

Data Index: 2224199 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 1.8621. Min Range: -1.8621

Max Act: 1.7940. Min Act: -0.1700

Data Index: 2634386 (Open Web Text)

Max Activating Token Index: 61