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

Dataset: Open Web Text

Neuron 610 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: 3.6809. Min Range: -3.6809

Max Act: 3.6809. Min Act: -0.1700

Data Index: 5443639 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.6796. Min Act: -0.1700

Data Index: 2960351 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.6261. Min Act: -0.1700

Data Index: 3184647 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.6456. Min Act: -0.1700

Data Index: 2874214 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.6104. Min Act: -0.1700

Data Index: 2848411 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5598. Min Act: -0.1700

Data Index: 630617 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1780045 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5850. Min Act: -0.1700

Data Index: 5886942 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5600. Min Act: -0.1700

Data Index: 7547893 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5392. Min Act: -0.1700

Data Index: 4150673 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5358. Min Act: -0.1700

Data Index: 3644694 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5548. Min Act: -0.1700

Data Index: 2222290 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5492. Min Act: -0.1700

Data Index: 1325046 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5359. Min Act: -0.1700

Data Index: 8135759 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5296. Min Act: -0.1700

Data Index: 7358427 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5322. Min Act: -0.1700

Data Index: 1245087 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5235. Min Act: -0.1700

Data Index: 7066385 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5376. Min Act: -0.1700

Data Index: 6220867 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5024. Min Act: -0.1700

Data Index: 1699841 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.6809. Min Range: -3.6809

Max Act: 3.5065. Min Act: -0.1700

Data Index: 5696493 (Open Web Text)

Max Activating Token Index: 8