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

Dataset: Open Web Text

Neuron 977 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: 3.0334. Min Range: -3.0334

Max Act: 3.0318. Min Act: -0.1700

Data Index: 931646 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0334. Min Act: -0.1700

Data Index: 5129531 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0134. Min Act: -0.1700

Data Index: 5039911 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0222. Min Act: -0.1700

Data Index: 2745775 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 7312918 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0041. Min Act: -0.1700

Data Index: 4917310 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 3298529 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 2157221 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 6406515 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 173243 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0088. Min Act: -0.1700

Data Index: 1526227 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0044. Min Act: -0.1700

Data Index: 2640763 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9757. Min Act: -0.1700

Data Index: 352704 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9666. Min Act: -0.1700

Data Index: 5964023 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9727. Min Act: -0.1700

Data Index: 8267380 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9670. Min Act: -0.1700

Data Index: 3987513 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9654. Min Act: -0.1700

Data Index: 6934315 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9521. Min Act: -0.1700

Data Index: 4050865 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9500. Min Act: -0.1700

Data Index: 3022085 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.9521. Min Act: -0.1700

Data Index: 2690658 (Open Web Text)

Max Activating Token Index: 2