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

Dataset: Open Web Text

Neuron 225 in Layer 4

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: 4.0730. Min Range: -4.0730

Max Act: 3.9827. Min Act: -0.1700

Data Index: 156359 (Open Web Text)

Max Activating Token Index: 803

Text #1

Max Range: 4.0730. Min Range: -4.0730

Max Act: 4.0730. Min Act: -0.1700

Data Index: 2442839 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 4.0730. Min Range: -4.0730

Max Act: 4.0273. Min Act: -0.1700

Data Index: 465200 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8893. Min Act: -0.1700

Data Index: 5269159 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9472. Min Act: -0.1700

Data Index: 8352332 (Open Web Text)

Max Activating Token Index: 884

Text #5

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9375. Min Act: -0.1700

Data Index: 5806440 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8580. Min Act: -0.1700

Data Index: 7302036 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8914. Min Act: -0.1700

Data Index: 7959114 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8480. Min Act: -0.1700

Data Index: 5389145 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9084. Min Act: -0.1700

Data Index: 702139 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8542. Min Act: -0.1700

Data Index: 7035075 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8644. Min Act: -0.1700

Data Index: 4842326 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8287. Min Act: -0.1700

Data Index: 7411602 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8397. Min Act: -0.1700

Data Index: 6296584 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8764. Min Act: -0.1700

Data Index: 4077825 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8428. Min Act: -0.1700

Data Index: 8094700 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8031. Min Act: -0.1700

Data Index: 554640 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8190. Min Act: -0.1700

Data Index: 4006480 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8370. Min Act: -0.1700

Data Index: 5927062 (Open Web Text)

Max Activating Token Index: 770

Text #19

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8335. Min Act: -0.1700

Data Index: 7963721 (Open Web Text)

Max Activating Token Index: 911