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

Dataset: Open Web Text

Neuron 1970 in Layer 6

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: 3.4492. Min Range: -3.4492

Max Act: 3.4492. Min Act: -0.1700

Data Index: 6401012 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2751. Min Act: -0.1700

Data Index: 5031920 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1723. Min Act: -0.1700

Data Index: 707787 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2062. Min Act: -0.1700

Data Index: 3781523 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1157. Min Act: -0.1700

Data Index: 8768659 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1403. Min Act: -0.1700

Data Index: 739180 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1702329 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1308. Min Act: -0.1700

Data Index: 3032905 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.1339. Min Act: -0.1700

Data Index: 3705894 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0790. Min Act: -0.1700

Data Index: 2122244 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0868. Min Act: -0.1700

Data Index: 6320386 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0904. Min Act: -0.1700

Data Index: 7565985 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0734. Min Act: -0.1700

Data Index: 4325170 (Open Web Text)

Max Activating Token Index: 266

Text #13

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0500. Min Act: -0.1700

Data Index: 1928523 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0451. Min Act: -0.1700

Data Index: 3582849 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0469. Min Act: -0.1700

Data Index: 3056606 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0275. Min Act: -0.1700

Data Index: 8380409 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0097. Min Act: -0.1700

Data Index: 572443 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.9946. Min Act: -0.1700

Data Index: 7175212 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0238. Min Act: -0.1700

Data Index: 867852 (Open Web Text)

Max Activating Token Index: 472