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

Dataset: Open Web Text

Neuron 68 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: 4.9272. Min Range: -4.9272

Max Act: 4.9272. Min Act: -0.1700

Data Index: 268578 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.8800. Min Act: -0.1700

Data Index: 8094166 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.8440. Min Act: -0.1700

Data Index: 5123444 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.8205. Min Act: -0.1700

Data Index: 6925243 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.8205. Min Act: -0.1700

Data Index: 332439 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7598. Min Act: -0.1700

Data Index: 6395302 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7702. Min Act: -0.1700

Data Index: 6576661 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7442. Min Act: -0.1700

Data Index: 1209425 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7317. Min Act: -0.1700

Data Index: 5848894 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7124. Min Act: -0.1700

Data Index: 5670469 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7248. Min Act: -0.1700

Data Index: 1934724 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6866. Min Act: -0.1700

Data Index: 891582 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6631. Min Act: -0.1700

Data Index: 4635451 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6805. Min Act: -0.1700

Data Index: 6017236 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6392. Min Act: -0.1700

Data Index: 1856380 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6328. Min Act: -0.1700

Data Index: 4078643 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6502. Min Act: -0.1700

Data Index: 8777801 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6160. Min Act: -0.1700

Data Index: 3178620 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6207. Min Act: -0.1700

Data Index: 6644656 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6029. Min Act: -0.1700

Data Index: 3784982 (Open Web Text)

Max Activating Token Index: 92