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

Dataset: Open Web Text

Neuron 143 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: 2.8170. Min Range: -2.8170

Max Act: 2.8170. Min Act: -0.1700

Data Index: 6498407 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7928. Min Act: -0.1700

Data Index: 2071999 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.8054. Min Act: -0.1700

Data Index: 4145290 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7648. Min Act: -0.1700

Data Index: 8411483 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7398. Min Act: -0.1700

Data Index: 5610735 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7541. Min Act: -0.1700

Data Index: 3341431 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7457. Min Act: -0.1700

Data Index: 1509064 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7541. Min Act: -0.1700

Data Index: 1576911 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7380. Min Act: -0.1700

Data Index: 3448475 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7164. Min Act: -0.1700

Data Index: 1417970 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7165. Min Act: -0.1700

Data Index: 1458548 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7096. Min Act: -0.1700

Data Index: 4765361 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6960. Min Act: -0.1700

Data Index: 8013330 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6960. Min Act: -0.1700

Data Index: 3973328 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6892. Min Act: -0.1700

Data Index: 4014686 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6615. Min Act: -0.1700

Data Index: 2295373 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6693. Min Act: -0.1700

Data Index: 5962950 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6548. Min Act: -0.1700

Data Index: 4044681 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6474. Min Act: -0.1700

Data Index: 2339072 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6408. Min Act: -0.1700

Data Index: 3616999 (Open Web Text)

Max Activating Token Index: 4