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

Dataset: Open Web Text

Neuron 73 in Layer 1

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: 3.9555. Min Range: -3.9555

Max Act: 3.9555. Min Act: -0.1699

Data Index: 4339096 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.9158. Min Act: -0.1673

Data Index: 6789079 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.8739. Min Act: -0.1676

Data Index: 7975483 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.8428. Min Act: -0.1673

Data Index: 2502538 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.8518. Min Act: -0.1693

Data Index: 7119900 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.8520. Min Act: -0.1673

Data Index: 472212 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.8436. Min Act: -0.1673

Data Index: 4271334 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7917. Min Act: -0.1673

Data Index: 6610373 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7930. Min Act: -0.1673

Data Index: 1858765 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7564. Min Act: -0.1673

Data Index: 7897493 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7964. Min Act: -0.1673

Data Index: 4296352 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7531. Min Act: -0.1673

Data Index: 4434395 (Open Web Text)

Max Activating Token Index: 655

Text #12

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7115. Min Act: -0.1673

Data Index: 2798142 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7196. Min Act: -0.1673

Data Index: 3339786 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7303. Min Act: -0.1673

Data Index: 6326676 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7149. Min Act: -0.1673

Data Index: 4259658 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7226. Min Act: -0.1673

Data Index: 2347373 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7171. Min Act: -0.1673

Data Index: 2555293 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7188. Min Act: -0.1673

Data Index: 5617003 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9555. Min Range: -3.9555

Max Act: 3.7089. Min Act: -0.1673

Data Index: 8761501 (Open Web Text)

Max Activating Token Index: 4