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

Dataset: Open Web Text

Neuron 2083 in Layer 5

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: 4.4697. Min Range: -4.4697

Max Act: 4.4694. Min Act: -0.1700

Data Index: 1943957 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4697. Min Act: -0.1700

Data Index: 251348 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4459. Min Act: -0.1700

Data Index: 5127432 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4295. Min Act: -0.1700

Data Index: 6891759 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4384. Min Act: -0.1700

Data Index: 7554024 (Open Web Text)

Max Activating Token Index: 336

Text #5

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4290. Min Act: -0.1700

Data Index: 7121416 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4457. Min Act: -0.1700

Data Index: 221215 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.4085. Min Act: -0.1700

Data Index: 3958817 (Open Web Text)

Max Activating Token Index: 964

Text #8

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3878. Min Act: -0.1700

Data Index: 4065864 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3954. Min Act: -0.1700

Data Index: 6468549 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3997. Min Act: -0.1700

Data Index: 3103664 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3658. Min Act: -0.1700

Data Index: 6806456 (Open Web Text)

Max Activating Token Index: 489

Text #12

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3552. Min Act: -0.1700

Data Index: 5398698 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3809. Min Act: -0.1700

Data Index: 140586 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3712. Min Act: -0.1700

Data Index: 8745807 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3290. Min Act: -0.1700

Data Index: 3958818 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3559. Min Act: -0.1700

Data Index: 251347 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3283. Min Act: -0.1700

Data Index: 5264897 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.3433. Min Act: -0.1700

Data Index: 8745808 (Open Web Text)

Max Activating Token Index: 127

Text #19

Max Range: 4.4697. Min Range: -4.4697

Max Act: 4.2968. Min Act: -0.1700

Data Index: 5127433 (Open Web Text)

Max Activating Token Index: 736