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

Dataset: Open Web Text

Neuron 990 in Layer 5

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: 3.0521. Min Range: -3.0521

Max Act: 3.0521. Min Act: -0.1700

Data Index: 1452753 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.9956. Min Act: -0.1700

Data Index: 497717 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.9957. Min Act: -0.1700

Data Index: 2422528 (Open Web Text)

Max Activating Token Index: 547

Text #3

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8729. Min Act: -0.1700

Data Index: 7955754 (Open Web Text)

Max Activating Token Index: 956

Text #4

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8571. Min Act: -0.1700

Data Index: 5671306 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8351. Min Act: -0.1700

Data Index: 1095064 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8153. Min Act: -0.1700

Data Index: 7435726 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.7897. Min Act: -0.1700

Data Index: 7692901 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8193. Min Act: -0.1700

Data Index: 5541799 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8288. Min Act: -0.1700

Data Index: 8691184 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8432. Min Act: -0.1700

Data Index: 7069024 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8116. Min Act: -0.1700

Data Index: 1336893 (Open Web Text)

Max Activating Token Index: 334

Text #12

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8170. Min Act: -0.1700

Data Index: 8208678 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8086. Min Act: -0.1700

Data Index: 257821 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8364. Min Act: -0.1700

Data Index: 1460810 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8294. Min Act: -0.1700

Data Index: 8252355 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8103. Min Act: -0.1700

Data Index: 3129860 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.7942. Min Act: -0.1700

Data Index: 8167016 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.8219. Min Act: -0.1700

Data Index: 7096106 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 3.0521. Min Range: -3.0521

Max Act: 2.7882. Min Act: -0.1700

Data Index: 2914057 (Open Web Text)

Max Activating Token Index: 521