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

Dataset: Open Web Text

Neuron 383 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: 1.8194. Min Range: -1.8194

Max Act: 1.8194. Min Act: -0.1700

Data Index: 5324676 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.8072. Min Act: -0.1700

Data Index: 2481658 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.8165. Min Act: -0.1700

Data Index: 467290 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7969. Min Act: -0.1700

Data Index: 5864195 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7768. Min Act: -0.1700

Data Index: 3290987 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7747. Min Act: -0.1700

Data Index: 7147237 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7709. Min Act: -0.1700

Data Index: 548179 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7780. Min Act: -0.1700

Data Index: 8239906 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7577. Min Act: -0.1700

Data Index: 3897588 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7616. Min Act: -0.1700

Data Index: 2399476 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7463. Min Act: -0.1700

Data Index: 4872276 (Open Web Text)

Max Activating Token Index: 56

Text #11

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7565. Min Act: -0.1700

Data Index: 6222524 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7351. Min Act: -0.1700

Data Index: 8060071 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7390. Min Act: -0.1700

Data Index: 4046433 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7363. Min Act: -0.1700

Data Index: 3398412 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7309. Min Act: -0.1700

Data Index: 6214455 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7437. Min Act: -0.1700

Data Index: 4432641 (Open Web Text)

Max Activating Token Index: 137

Text #17

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7274. Min Act: -0.1700

Data Index: 1746730 (Open Web Text)

Max Activating Token Index: 155

Text #18

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7320. Min Act: -0.1700

Data Index: 459861 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.7355. Min Act: -0.1700

Data Index: 424486 (Open Web Text)

Max Activating Token Index: 48