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

Dataset: Open Web Text

Neuron 913 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: 3.0805. Min Range: -3.0805

Max Act: 3.0660. Min Act: -0.1700

Data Index: 1927070 (Open Web Text)

Max Activating Token Index: 715

Text #1

Max Range: 3.0805. Min Range: -3.0805

Max Act: 3.0805. Min Act: -0.1700

Data Index: 7477104 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.0805. Min Range: -3.0805

Max Act: 3.0638. Min Act: -0.1700

Data Index: 394725 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 3.0805. Min Range: -3.0805

Max Act: 3.0292. Min Act: -0.1700

Data Index: 198960 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.0805. Min Range: -3.0805

Max Act: 3.0242. Min Act: -0.1700

Data Index: 724175 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9970. Min Act: -0.1700

Data Index: 1250026 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9491. Min Act: -0.1700

Data Index: 8384206 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9245. Min Act: -0.1700

Data Index: 7513154 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9313. Min Act: -0.1700

Data Index: 2874189 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9304. Min Act: -0.1700

Data Index: 4515516 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9247. Min Act: -0.1700

Data Index: 1429177 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9474. Min Act: -0.1700

Data Index: 251279 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8972. Min Act: -0.1700

Data Index: 3180599 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.9073. Min Act: -0.1700

Data Index: 4528985 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8702. Min Act: -0.1700

Data Index: 3676934 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8994. Min Act: -0.1700

Data Index: 4394229 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8740. Min Act: -0.1700

Data Index: 3386678 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8869. Min Act: -0.1700

Data Index: 7070022 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8628. Min Act: -0.1700

Data Index: 1478326 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.0805. Min Range: -3.0805

Max Act: 2.8713. Min Act: -0.1700

Data Index: 1489584 (Open Web Text)

Max Activating Token Index: 617