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

Dataset: Open Web Text

Neuron 1937 in Layer 2

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: 2.9199. Min Range: -2.9199

Max Act: 2.9199. Min Act: -0.1698

Data Index: 3467060 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8999. Min Act: -0.1685

Data Index: 3221547 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8877. Min Act: -0.1668

Data Index: 598487 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8960. Min Act: -0.1668

Data Index: 2831726 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8897. Min Act: -0.1682

Data Index: 2291146 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8563. Min Act: -0.1699

Data Index: 5952559 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8720. Min Act: -0.1694

Data Index: 6310843 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8621. Min Act: -0.1602

Data Index: 7403154 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8575. Min Act: -0.1699

Data Index: 3446692 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8452. Min Act: -0.1699

Data Index: 1187121 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8615. Min Act: -0.1692

Data Index: 5502849 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8558. Min Act: -0.1700

Data Index: 5833565 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8428. Min Act: -0.1699

Data Index: 233999 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8478. Min Act: -0.1699

Data Index: 2934358 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8520. Min Act: -0.1698

Data Index: 3020042 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8480. Min Act: -0.1680

Data Index: 521754 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8379. Min Act: -0.1527

Data Index: 3185351 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8593. Min Act: -0.1649

Data Index: 8640532 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8506. Min Act: -0.1665

Data Index: 3335215 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9199. Min Range: -2.9199

Max Act: 2.8515. Min Act: -0.1653

Data Index: 885081 (Open Web Text)

Max Activating Token Index: 3