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

Dataset: Open Web Text

Neuron 57 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: 3.0648. Min Range: -3.0648

Max Act: 3.0648. Min Act: -0.1700

Data Index: 6709763 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9736. Min Act: -0.1700

Data Index: 7689949 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9577. Min Act: -0.1700

Data Index: 2044070 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9898. Min Act: -0.1700

Data Index: 6942580 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9561. Min Act: -0.1700

Data Index: 2716333 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9645. Min Act: -0.1700

Data Index: 624180 (Open Web Text)

Max Activating Token Index: 896

Text #6

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9579. Min Act: -0.1700

Data Index: 8421433 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9442. Min Act: -0.1700

Data Index: 4175309 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9273. Min Act: -0.1700

Data Index: 4141643 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9603. Min Act: -0.1700

Data Index: 7091548 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9527. Min Act: -0.1700

Data Index: 985468 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9581. Min Act: -0.1700

Data Index: 8763544 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9391. Min Act: -0.1700

Data Index: 2825594 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9478. Min Act: -0.1700

Data Index: 1176765 (Open Web Text)

Max Activating Token Index: 409

Text #14

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9429. Min Act: -0.1700

Data Index: 8344791 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9287. Min Act: -0.1700

Data Index: 5788862 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9134. Min Act: -0.1700

Data Index: 5962862 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9461. Min Act: -0.1700

Data Index: 6405498 (Open Web Text)

Max Activating Token Index: 425

Text #18

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9308. Min Act: -0.1700

Data Index: 6999740 (Open Web Text)

Max Activating Token Index: 55

Text #19

Max Range: 3.0648. Min Range: -3.0648

Max Act: 2.9224. Min Act: -0.1700

Data Index: 6980282 (Open Web Text)

Max Activating Token Index: 558