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

Dataset: Open Web Text

Neuron 2886 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: 5.0691. Min Range: -5.0691

Max Act: 5.0691. Min Act: -0.1700

Data Index: 906442 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 5.0691. Min Range: -5.0691

Max Act: 5.0641. Min Act: -0.1700

Data Index: 8542764 (Open Web Text)

Max Activating Token Index: 119

Text #2

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9706. Min Act: -0.1700

Data Index: 4920551 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9673. Min Act: -0.1700

Data Index: 6468847 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9589. Min Act: -0.1700

Data Index: 1238947 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9535. Min Act: -0.1700

Data Index: 7917593 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9213. Min Act: -0.1700

Data Index: 994728 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9301. Min Act: -0.1700

Data Index: 2278058 (Open Web Text)

Max Activating Token Index: 379

Text #8

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9134. Min Act: -0.1700

Data Index: 2837829 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8823. Min Act: -0.1700

Data Index: 3208960 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8906. Min Act: -0.1700

Data Index: 5737827 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.9191. Min Act: -0.1700

Data Index: 3987765 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8597. Min Act: -0.1700

Data Index: 3225117 (Open Web Text)

Max Activating Token Index: 294

Text #13

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8572. Min Act: -0.1700

Data Index: 2789282 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8688. Min Act: -0.1700

Data Index: 8633622 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8587. Min Act: -0.1700

Data Index: 7142644 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8654. Min Act: -0.1700

Data Index: 6802242 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8507. Min Act: -0.1700

Data Index: 2487820 (Open Web Text)

Max Activating Token Index: 175

Text #18

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8549. Min Act: -0.1700

Data Index: 811128 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 5.0691. Min Range: -5.0691

Max Act: 4.8599. Min Act: -0.1700

Data Index: 5124584 (Open Web Text)

Max Activating Token Index: 853