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

Dataset: Open Web Text

Neuron 234 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: 1.8031. Min Range: -1.8031

Max Act: 1.8021. Min Act: -0.1700

Data Index: 935148 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.8031. Min Act: -0.1692

Data Index: 5239976 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7820. Min Act: -0.1700

Data Index: 315903 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7883. Min Act: -0.1692

Data Index: 2405112 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7684. Min Act: -0.1700

Data Index: 6877645 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7668. Min Act: -0.1697

Data Index: 1385736 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7633. Min Act: -0.1698

Data Index: 3893953 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7499. Min Act: -0.1700

Data Index: 8246335 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7397. Min Act: -0.1697

Data Index: 933423 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7407. Min Act: -0.1700

Data Index: 3181920 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7397. Min Act: -0.1700

Data Index: 7268464 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7352. Min Act: -0.1700

Data Index: 7089413 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7273. Min Act: -0.1700

Data Index: 2446555 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7233. Min Act: -0.1699

Data Index: 495582 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7298. Min Act: -0.1700

Data Index: 5037024 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7265. Min Act: -0.1700

Data Index: 8026280 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7140. Min Act: -0.1700

Data Index: 1119979 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7172. Min Act: -0.1700

Data Index: 4467913 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7144. Min Act: -0.1695

Data Index: 3194225 (Open Web Text)

Max Activating Token Index: 931

Text #19

Max Range: 1.8031. Min Range: -1.8031

Max Act: 1.7181. Min Act: -0.1693

Data Index: 5313113 (Open Web Text)

Max Activating Token Index: 2