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

Dataset: Open Web Text

Neuron 138 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: 3.9253. Min Range: -3.9253

Max Act: 3.9253. Min Act: -0.1700

Data Index: 926257 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8505. Min Act: -0.1700

Data Index: 2417691 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8541. Min Act: -0.1700

Data Index: 1400634 (Open Web Text)

Max Activating Token Index: 991

Text #3

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8335. Min Act: -0.1700

Data Index: 3617425 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8406. Min Act: -0.1700

Data Index: 3342711 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8134. Min Act: -0.1700

Data Index: 8638552 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8131. Min Act: -0.1700

Data Index: 1114907 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8028. Min Act: -0.1700

Data Index: 6054255 (Open Web Text)

Max Activating Token Index: 985

Text #8

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8260. Min Act: -0.1700

Data Index: 5956810 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8442. Min Act: -0.1700

Data Index: 1591119 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8084. Min Act: -0.1700

Data Index: 5280912 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7962. Min Act: -0.1700

Data Index: 2141229 (Open Web Text)

Max Activating Token Index: 193

Text #12

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.8136. Min Act: -0.1700

Data Index: 3920874 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7730. Min Act: -0.1700

Data Index: 5389728 (Open Web Text)

Max Activating Token Index: 133

Text #14

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7834. Min Act: -0.1700

Data Index: 1241767 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7709. Min Act: -0.1700

Data Index: 1012491 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7626. Min Act: -0.1700

Data Index: 3397202 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7698. Min Act: -0.1700

Data Index: 5883065 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7630. Min Act: -0.1700

Data Index: 4175684 (Open Web Text)

Max Activating Token Index: 648

Text #19

Max Range: 3.9253. Min Range: -3.9253

Max Act: 3.7430. Min Act: -0.1700

Data Index: 6081538 (Open Web Text)

Max Activating Token Index: 548