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

Dataset: Open Web Text

Neuron 1786 in Layer 3

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: 3.2323. Min Range: -3.2323

Max Act: 3.2323. Min Act: -0.1700

Data Index: 4687008 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1542. Min Act: -0.1700

Data Index: 7614709 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0914. Min Act: -0.1700

Data Index: 4249717 (Open Web Text)

Max Activating Token Index: 70

Text #3

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1017. Min Act: -0.1700

Data Index: 3050406 (Open Web Text)

Max Activating Token Index: 679

Text #4

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1968655 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1075. Min Act: -0.1700

Data Index: 6484366 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.1261. Min Act: -0.1700

Data Index: 1632894 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0983. Min Act: -0.1700

Data Index: 7835737 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0834. Min Act: -0.1700

Data Index: 8318412 (Open Web Text)

Max Activating Token Index: 762

Text #9

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0794. Min Act: -0.1700

Data Index: 6756673 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0833. Min Act: -0.1700

Data Index: 6808828 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0545. Min Act: -0.1700

Data Index: 601426 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0638. Min Act: -0.1700

Data Index: 5891339 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0574. Min Act: -0.1700

Data Index: 7680083 (Open Web Text)

Max Activating Token Index: 733

Text #14

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0578. Min Act: -0.1700

Data Index: 4762064 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0191. Min Act: -0.1700

Data Index: 7462316 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0487. Min Act: -0.1700

Data Index: 5084803 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0387. Min Act: -0.1700

Data Index: 3708953 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0459. Min Act: -0.1700

Data Index: 4439961 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 3.2323. Min Range: -3.2323

Max Act: 3.0122. Min Act: -0.1700

Data Index: 8032530 (Open Web Text)

Max Activating Token Index: 960