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

Dataset: Open Web Text

Neuron 208 in Layer 6

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: 4.7217. Min Range: -4.7217

Max Act: 4.7217. Min Act: -0.1700

Data Index: 5992169 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.4883. Min Act: -0.1700

Data Index: 5355468 (Open Web Text)

Max Activating Token Index: 987

Text #2

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.4129. Min Act: -0.1700

Data Index: 4283829 (Open Web Text)

Max Activating Token Index: 898

Text #3

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.3333. Min Act: -0.1700

Data Index: 8520179 (Open Web Text)

Max Activating Token Index: 977

Text #4

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2621. Min Act: -0.1700

Data Index: 3190991 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2250. Min Act: -0.1700

Data Index: 1572835 (Open Web Text)

Max Activating Token Index: 657

Text #6

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1985. Min Act: -0.1700

Data Index: 6196413 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2214. Min Act: -0.1700

Data Index: 3021697 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1555. Min Act: -0.1700

Data Index: 5691279 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2168. Min Act: -0.1700

Data Index: 4720840 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2001. Min Act: -0.1700

Data Index: 4698061 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1976. Min Act: -0.1700

Data Index: 8053350 (Open Web Text)

Max Activating Token Index: 239

Text #12

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.2077. Min Act: -0.1700

Data Index: 1794603 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1629. Min Act: -0.1700

Data Index: 6946731 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1602. Min Act: -0.1700

Data Index: 2915669 (Open Web Text)

Max Activating Token Index: 667

Text #15

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1631. Min Act: -0.1700

Data Index: 6225711 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1703. Min Act: -0.1700

Data Index: 3986872 (Open Web Text)

Max Activating Token Index: 785

Text #17

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1218. Min Act: -0.1700

Data Index: 4313322 (Open Web Text)

Max Activating Token Index: 831

Text #18

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1630. Min Act: -0.1700

Data Index: 3619258 (Open Web Text)

Max Activating Token Index: 410

Text #19

Max Range: 4.7217. Min Range: -4.7217

Max Act: 4.1532. Min Act: -0.1700

Data Index: 6441518 (Open Web Text)

Max Activating Token Index: 274