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

Dataset: Open Web Text

Neuron 734 in Layer 3

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: 5.1217. Min Range: -5.1217

Max Act: 5.1217. Min Act: -0.1700

Data Index: 280079 (Open Web Text)

Max Activating Token Index: 820

Text #1

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.1071. Min Act: -0.1700

Data Index: 6954410 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 5.1217. Min Range: -5.1217

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1180881 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.9736. Min Act: -0.1700

Data Index: 1320691 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.9404. Min Act: -0.1700

Data Index: 8260462 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8974. Min Act: -0.1700

Data Index: 5066869 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.9123. Min Act: -0.1700

Data Index: 7042868 (Open Web Text)

Max Activating Token Index: 793

Text #7

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.9053. Min Act: -0.1700

Data Index: 3459685 (Open Web Text)

Max Activating Token Index: 924

Text #8

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8542. Min Act: -0.1700

Data Index: 1062559 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8932. Min Act: -0.1700

Data Index: 5963646 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.7378. Min Act: -0.1700

Data Index: 688948 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.7687. Min Act: -0.1700

Data Index: 3393150 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8164. Min Act: -0.1700

Data Index: 1643927 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.7273. Min Act: -0.1700

Data Index: 4914191 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8333. Min Act: -0.1700

Data Index: 3374243 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8334. Min Act: -0.1700

Data Index: 2519836 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8463. Min Act: -0.1700

Data Index: 5515802 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.8152. Min Act: -0.1700

Data Index: 751259 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.7728. Min Act: -0.1700

Data Index: 5424005 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 5.1217. Min Range: -5.1217

Max Act: 4.7139. Min Act: -0.1700

Data Index: 2921113 (Open Web Text)

Max Activating Token Index: 181