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

Dataset: Open Web Text

Neuron 2430 in Layer 4

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: 1.8860. Min Range: -1.8860

Max Act: 1.8860. Min Act: -0.1700

Data Index: 2183262 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8471. Min Act: -0.1700

Data Index: 4064347 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8461. Min Act: -0.1700

Data Index: 2770186 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8461. Min Act: -0.1700

Data Index: 750192 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8260. Min Act: -0.1700

Data Index: 2162340 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8167. Min Act: -0.1700

Data Index: 7398158 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8115. Min Act: -0.1700

Data Index: 887978 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.8143. Min Act: -0.1700

Data Index: 7824330 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7882. Min Act: -0.1700

Data Index: 8008871 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7899. Min Act: -0.1700

Data Index: 7775328 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7836. Min Act: -0.1700

Data Index: 8036263 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7860. Min Act: -0.1700

Data Index: 8460613 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7725. Min Act: -0.1700

Data Index: 2699813 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7616. Min Act: -0.1700

Data Index: 3216231 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7676. Min Act: -0.1700

Data Index: 4291424 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7560. Min Act: -0.1700

Data Index: 8279508 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7528. Min Act: -0.1700

Data Index: 1462291 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7546. Min Act: -0.1700

Data Index: 8248315 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7457. Min Act: -0.1700

Data Index: 7053343 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 1.8860. Min Range: -1.8860

Max Act: 1.7231. Min Act: -0.1700

Data Index: 30618 (Open Web Text)

Max Activating Token Index: 40