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

Dataset: Open Web Text

Neuron 354 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: 6.2790. Min Range: -6.2790

Max Act: 6.2790. Min Act: -0.1700

Data Index: 6011281 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1525. Min Act: -0.1700

Data Index: 7670677 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1534. Min Act: -0.1700

Data Index: 7394728 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1292. Min Act: -0.1700

Data Index: 1175129 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1577. Min Act: -0.1699

Data Index: 4355206 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1389. Min Act: -0.1700

Data Index: 7332372 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.1642. Min Act: -0.1700

Data Index: 3130535 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0806. Min Act: -0.1700

Data Index: 2146532 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0689. Min Act: -0.1700

Data Index: 205340 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0571. Min Act: -0.1700

Data Index: 1697926 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0482. Min Act: -0.1700

Data Index: 4803231 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0247. Min Act: -0.1700

Data Index: 6652104 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0417. Min Act: -0.1700

Data Index: 1949453 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.2790. Min Range: -6.2790

Max Act: 5.9931. Min Act: -0.1700

Data Index: 2602747 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0247. Min Act: -0.1700

Data Index: 729137 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0251. Min Act: -0.1700

Data Index: 3263419 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0205. Min Act: -0.1700

Data Index: 3141466 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 6.2790. Min Range: -6.2790

Max Act: 5.9867. Min Act: -0.1700

Data Index: 4885610 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0178. Min Act: -0.1700

Data Index: 800317 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 6.2790. Min Range: -6.2790

Max Act: 6.0247. Min Act: -0.1700

Data Index: 379098 (Open Web Text)

Max Activating Token Index: 4