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

Dataset: Open Web Text

Neuron 3010 in Layer 6

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: 3.6689. Min Range: -3.6689

Max Act: 3.6661. Min Act: -0.1700

Data Index: 6236006 (Open Web Text)

Max Activating Token Index: 727

Text #1

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.6689. Min Act: -0.1700

Data Index: 799600 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.5513. Min Act: -0.1700

Data Index: 6633720 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.5206. Min Act: -0.1700

Data Index: 3508890 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.5372. Min Act: -0.1700

Data Index: 2641528 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4890. Min Act: -0.1700

Data Index: 726289 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.5026. Min Act: -0.1700

Data Index: 2323150 (Open Web Text)

Max Activating Token Index: 95

Text #7

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.5149. Min Act: -0.1700

Data Index: 3406264 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4725. Min Act: -0.1700

Data Index: 1208856 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4608. Min Act: -0.1700

Data Index: 5948396 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4305. Min Act: -0.1700

Data Index: 3664512 (Open Web Text)

Max Activating Token Index: 404

Text #11

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4646. Min Act: -0.1700

Data Index: 4841457 (Open Web Text)

Max Activating Token Index: 801

Text #12

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4659. Min Act: -0.1700

Data Index: 1206218 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4233. Min Act: -0.1700

Data Index: 3729989 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4373. Min Act: -0.1700

Data Index: 5029840 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4254. Min Act: -0.1700

Data Index: 1206217 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4154. Min Act: -0.1700

Data Index: 5688660 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4191. Min Act: -0.1700

Data Index: 2906323 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4591. Min Act: -0.1700

Data Index: 7152100 (Open Web Text)

Max Activating Token Index: 529

Text #19

Max Range: 3.6689. Min Range: -3.6689

Max Act: 3.4246. Min Act: -0.1700

Data Index: 6823306 (Open Web Text)

Max Activating Token Index: 426