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

Dataset: Open Web Text

Neuron 2202 in Layer 3

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: 3.6180. Min Range: -3.6180

Max Act: 3.6180. Min Act: -0.1700

Data Index: 8516104 (Open Web Text)

Max Activating Token Index: 191

Text #1

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.5301. Min Act: -0.1700

Data Index: 3866607 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.5010. Min Act: -0.1700

Data Index: 6182218 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.4411. Min Act: -0.1700

Data Index: 1874359 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.4139. Min Act: -0.1700

Data Index: 2046453 (Open Web Text)

Max Activating Token Index: 547

Text #5

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.2947. Min Act: -0.1700

Data Index: 6037301 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3766. Min Act: -0.1700

Data Index: 2686437 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3600. Min Act: -0.1700

Data Index: 373225 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3882. Min Act: -0.1700

Data Index: 8591322 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3579. Min Act: -0.1700

Data Index: 1755294 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3699. Min Act: -0.1700

Data Index: 1367940 (Open Web Text)

Max Activating Token Index: 790

Text #11

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3451. Min Act: -0.1700

Data Index: 2359480 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3683. Min Act: -0.1700

Data Index: 8557848 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3834. Min Act: -0.1700

Data Index: 3484654 (Open Web Text)

Max Activating Token Index: 658

Text #14

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3787. Min Act: -0.1700

Data Index: 3150897 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3790. Min Act: -0.1700

Data Index: 562162 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3505. Min Act: -0.1700

Data Index: 5848813 (Open Web Text)

Max Activating Token Index: 212

Text #17

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3331. Min Act: -0.1700

Data Index: 4037705 (Open Web Text)

Max Activating Token Index: 360

Text #18

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.3259. Min Act: -0.1700

Data Index: 2810785 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.6180. Min Range: -3.6180

Max Act: 3.2872. Min Act: -0.1700

Data Index: 3234122 (Open Web Text)

Max Activating Token Index: 323