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

Dataset: Open Web Text

Neuron 1652 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: 5.4214. Min Range: -5.4214

Max Act: 5.4214. Min Act: -0.1700

Data Index: 8545601 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.3794. Min Act: -0.1700

Data Index: 6649769 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2485. Min Act: -0.1700

Data Index: 7275831 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2592. Min Act: -0.1700

Data Index: 3238787 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2577. Min Act: -0.1700

Data Index: 1211094 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2626. Min Act: -0.1700

Data Index: 333470 (Open Web Text)

Max Activating Token Index: 976

Text #6

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2499. Min Act: -0.1700

Data Index: 4709348 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2485. Min Act: -0.1700

Data Index: 4943397 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2243. Min Act: -0.1700

Data Index: 2052036 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.2289. Min Act: -0.1700

Data Index: 8225978 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1638. Min Act: -0.1700

Data Index: 1408444 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1458. Min Act: -0.1700

Data Index: 5201373 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1279. Min Act: -0.1700

Data Index: 5418580 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1623. Min Act: -0.1700

Data Index: 2959123 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1416. Min Act: -0.1700

Data Index: 1549258 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1512. Min Act: -0.1700

Data Index: 7412074 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1658. Min Act: -0.1700

Data Index: 7444240 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1589. Min Act: -0.1700

Data Index: 3457423 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1822. Min Act: -0.1700

Data Index: 4328453 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 5.4214. Min Range: -5.4214

Max Act: 5.1403. Min Act: -0.1700

Data Index: 3539043 (Open Web Text)

Max Activating Token Index: 275