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

Dataset: Open Web Text

Neuron 192 in Layer 1

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: 1.7775. Min Range: -1.7775

Max Act: 1.7775. Min Act: -0.1483

Data Index: 7423445 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7628. Min Act: -0.1695

Data Index: 5441802 (Open Web Text)

Max Activating Token Index: 778

Text #2

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7374. Min Act: -0.1700

Data Index: 1844549 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7376. Min Act: -0.1687

Data Index: 5813643 (Open Web Text)

Max Activating Token Index: 319

Text #4

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7404. Min Act: -0.1698

Data Index: 1674412 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7376. Min Act: -0.1700

Data Index: 7862762 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7238. Min Act: -0.1550

Data Index: 4104318 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7222. Min Act: -0.1700

Data Index: 18336 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7286. Min Act: -0.1700

Data Index: 2494542 (Open Web Text)

Max Activating Token Index: 162

Text #9

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7287. Min Act: -0.1700

Data Index: 2740714 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7202. Min Act: -0.1700

Data Index: 5208935 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7155. Min Act: -0.1691

Data Index: 8759567 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7005. Min Act: -0.1700

Data Index: 7793089 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.7033. Min Act: -0.1700

Data Index: 6484 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6991. Min Act: -0.1652

Data Index: 1592453 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6990. Min Act: -0.1693

Data Index: 269183 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6912. Min Act: -0.1700

Data Index: 6342240 (Open Web Text)

Max Activating Token Index: 821

Text #17

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6915. Min Act: -0.1700

Data Index: 6749111 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6918. Min Act: -0.1700

Data Index: 4414555 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 1.7775. Min Range: -1.7775

Max Act: 1.6998. Min Act: -0.1700

Data Index: 1291057 (Open Web Text)

Max Activating Token Index: 160