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

Dataset: Open Web Text

Neuron 1269 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: 4.0374. Min Range: -4.0374

Max Act: 4.0374. Min Act: -0.1700

Data Index: 3552086 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 4.0374. Min Range: -4.0374

Max Act: 4.0268. Min Act: -0.1700

Data Index: 6297483 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.9180. Min Act: -0.1700

Data Index: 61080 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8972. Min Act: -0.1700

Data Index: 2931399 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8587. Min Act: -0.1700

Data Index: 2767939 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8660. Min Act: -0.1700

Data Index: 5131264 (Open Web Text)

Max Activating Token Index: 977

Text #6

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8481. Min Act: -0.1700

Data Index: 4646013 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8134. Min Act: -0.1700

Data Index: 4999131 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7818. Min Act: -0.1700

Data Index: 3591509 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8004. Min Act: -0.1700

Data Index: 5407604 (Open Web Text)

Max Activating Token Index: 104

Text #10

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7728. Min Act: -0.1700

Data Index: 7641761 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.8033. Min Act: -0.1700

Data Index: 7635280 (Open Web Text)

Max Activating Token Index: 29

Text #12

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7318. Min Act: -0.1700

Data Index: 7994448 (Open Web Text)

Max Activating Token Index: 295

Text #13

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7784. Min Act: -0.1700

Data Index: 3155228 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7677. Min Act: -0.1700

Data Index: 449617 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7645. Min Act: -0.1700

Data Index: 5871209 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7630. Min Act: -0.1700

Data Index: 1753324 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7425. Min Act: -0.1700

Data Index: 5068103 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7519. Min Act: -0.1700

Data Index: 5512366 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.0374. Min Range: -4.0374

Max Act: 3.7858. Min Act: -0.1700

Data Index: 3728073 (Open Web Text)

Max Activating Token Index: 39