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

Dataset: Open Web Text

Neuron 3042 in Layer 2

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: 3.1224. Min Range: -3.1224

Max Act: 3.1224. Min Act: -0.1697

Data Index: 5107884 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9508. Min Act: -0.1700

Data Index: 6456340 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8909. Min Act: -0.1700

Data Index: 7793589 (Open Web Text)

Max Activating Token Index: 170

Text #3

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8945. Min Act: -0.1700

Data Index: 3602350 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8666. Min Act: -0.1700

Data Index: 2548616 (Open Web Text)

Max Activating Token Index: 425

Text #5

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8442. Min Act: -0.1700

Data Index: 1691054 (Open Web Text)

Max Activating Token Index: 447

Text #6

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8478. Min Act: -0.1700

Data Index: 5063735 (Open Web Text)

Max Activating Token Index: 239

Text #7

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8303. Min Act: -0.1700

Data Index: 4531617 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8280. Min Act: -0.1700

Data Index: 3731132 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8042. Min Act: -0.1700

Data Index: 4569305 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.8004. Min Act: -0.1700

Data Index: 47574 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7906. Min Act: -0.1700

Data Index: 1271847 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7838. Min Act: -0.1700

Data Index: 1721556 (Open Web Text)

Max Activating Token Index: 749

Text #13

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7692. Min Act: -0.1700

Data Index: 8275089 (Open Web Text)

Max Activating Token Index: 880

Text #14

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7574. Min Act: -0.1700

Data Index: 4669140 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7459. Min Act: -0.1700

Data Index: 5845263 (Open Web Text)

Max Activating Token Index: 808

Text #16

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7422. Min Act: -0.1700

Data Index: 8721777 (Open Web Text)

Max Activating Token Index: 526

Text #17

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7572. Min Act: -0.1700

Data Index: 7005779 (Open Web Text)

Max Activating Token Index: 332

Text #18

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7449. Min Act: -0.1700

Data Index: 2428602 (Open Web Text)

Max Activating Token Index: 409

Text #19

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.7293. Min Act: -0.1700

Data Index: 4205997 (Open Web Text)

Max Activating Token Index: 398