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

Dataset: Open Web Text

Neuron 1850 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: 1.8389. Min Range: -1.8389

Max Act: 1.8389. Min Act: -0.1700

Data Index: 3773147 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7350. Min Act: -0.1700

Data Index: 5260208 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.7085. Min Act: -0.1700

Data Index: 2029 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6869. Min Act: -0.1700

Data Index: 2001110 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6664. Min Act: -0.1700

Data Index: 1986726 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6617. Min Act: -0.1700

Data Index: 3737834 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6534. Min Act: -0.1700

Data Index: 2993161 (Open Web Text)

Max Activating Token Index: 342

Text #7

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6620. Min Act: -0.1698

Data Index: 3383183 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6638. Min Act: -0.1700

Data Index: 332972 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6551. Min Act: -0.1700

Data Index: 7426308 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6493. Min Act: -0.1700

Data Index: 4715343 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6575. Min Act: -0.1698

Data Index: 964628 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6302. Min Act: -0.1700

Data Index: 1751311 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6530. Min Act: -0.1700

Data Index: 5594048 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6374. Min Act: -0.1699

Data Index: 2982722 (Open Web Text)

Max Activating Token Index: 960

Text #15

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6292. Min Act: -0.1700

Data Index: 1063359 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6271. Min Act: -0.1700

Data Index: 6590322 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6466. Min Act: -0.1700

Data Index: 5511409 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6390. Min Act: -0.1700

Data Index: 5557273 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6341. Min Act: -0.1700

Data Index: 1823691 (Open Web Text)

Max Activating Token Index: 403