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

Dataset: Open Web Text

Neuron 2835 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: 4.0361. Min Range: -4.0361

Max Act: 4.0361. Min Act: -0.1700

Data Index: 3396954 (Open Web Text)

Max Activating Token Index: 863

Text #1

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9601. Min Act: -0.1700

Data Index: 8095416 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9996. Min Act: -0.1700

Data Index: 5242980 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9340. Min Act: -0.1700

Data Index: 7744208 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9491. Min Act: -0.1700

Data Index: 4238353 (Open Web Text)

Max Activating Token Index: 900

Text #5

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9298. Min Act: -0.1700

Data Index: 6813100 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9084. Min Act: -0.1700

Data Index: 1336289 (Open Web Text)

Max Activating Token Index: 632

Text #7

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9167. Min Act: -0.1700

Data Index: 6675384 (Open Web Text)

Max Activating Token Index: 844

Text #8

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9326. Min Act: -0.1700

Data Index: 8414280 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8550. Min Act: -0.1700

Data Index: 5279979 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8354. Min Act: -0.1700

Data Index: 2789971 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8305. Min Act: -0.1700

Data Index: 1130262 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8366. Min Act: -0.1700

Data Index: 4400572 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8162. Min Act: -0.1700

Data Index: 4357886 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8250. Min Act: -0.1700

Data Index: 7203449 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8023. Min Act: -0.1700

Data Index: 7321488 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.7850. Min Act: -0.1700

Data Index: 1114051 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.7753. Min Act: -0.1700

Data Index: 18238 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.7812. Min Act: -0.1700

Data Index: 6897205 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.7711. Min Act: -0.1700

Data Index: 2214416 (Open Web Text)

Max Activating Token Index: 687