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

Dataset: Open Web Text

Neuron 258 in Layer 5

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: 4.0617. Min Range: -4.0617

Max Act: 4.0617. Min Act: -0.1700

Data Index: 8131950 (Open Web Text)

Max Activating Token Index: 486

Text #1

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.9378. Min Act: -0.1700

Data Index: 412956 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.9273. Min Act: -0.1700

Data Index: 677056 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8494. Min Act: -0.1700

Data Index: 3933394 (Open Web Text)

Max Activating Token Index: 788

Text #4

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8403. Min Act: -0.1700

Data Index: 7625839 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8679. Min Act: -0.1700

Data Index: 5339954 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1606358 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8086. Min Act: -0.1700

Data Index: 3652131 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.8167. Min Act: -0.1700

Data Index: 5717705 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7582. Min Act: -0.1700

Data Index: 7157847 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1165452 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7496. Min Act: -0.1700

Data Index: 5455721 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7998. Min Act: -0.1700

Data Index: 7077035 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7611. Min Act: -0.1700

Data Index: 4506723 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7783. Min Act: -0.1700

Data Index: 2621006 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7672. Min Act: -0.1700

Data Index: 4134082 (Open Web Text)

Max Activating Token Index: 664

Text #16

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7393. Min Act: -0.1700

Data Index: 6272165 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7655. Min Act: -0.1700

Data Index: 248247 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7520. Min Act: -0.1700

Data Index: 6523943 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 4.0617. Min Range: -4.0617

Max Act: 3.7572. Min Act: -0.1700

Data Index: 3176518 (Open Web Text)

Max Activating Token Index: 937