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

Dataset: Open Web Text

Neuron 2450 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: 4.3423. Min Range: -4.3423

Max Act: 4.3423. Min Act: -0.1700

Data Index: 1219488 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1812. Min Act: -0.1700

Data Index: 6609911 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1874. Min Act: -0.1700

Data Index: 3815748 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0963. Min Act: -0.1700

Data Index: 115095 (Open Web Text)

Max Activating Token Index: 763

Text #4

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0816. Min Act: -0.1700

Data Index: 6209443 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1429. Min Act: -0.1700

Data Index: 3351815 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1121. Min Act: -0.1700

Data Index: 8433096 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.1168. Min Act: -0.1700

Data Index: 2271263 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0422. Min Act: -0.1700

Data Index: 1834188 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0397. Min Act: -0.1700

Data Index: 4707010 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0148. Min Act: -0.1700

Data Index: 2245515 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0207. Min Act: -0.1700

Data Index: 4269886 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0125. Min Act: -0.1700

Data Index: 6273529 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 4.3423. Min Range: -4.3423

Max Act: 4.0053. Min Act: -0.1700

Data Index: 8231772 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9701. Min Act: -0.1700

Data Index: 14665 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9843. Min Act: -0.1700

Data Index: 3012970 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9851. Min Act: -0.1700

Data Index: 5167668 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9467. Min Act: -0.1700

Data Index: 1024258 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9514. Min Act: -0.1700

Data Index: 671116 (Open Web Text)

Max Activating Token Index: 512

Text #19

Max Range: 4.3423. Min Range: -4.3423

Max Act: 3.9419. Min Act: -0.1700

Data Index: 3877561 (Open Web Text)

Max Activating Token Index: 462