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

Dataset: Open Web Text

Neuron 1878 in Layer 4

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: -0.1700

Data Index: 6057576 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0629. Min Act: -0.1700

Data Index: 3529449 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0430. Min Act: -0.1700

Data Index: 6465436 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0357. Min Act: -0.1700

Data Index: 7283551 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0511. Min Act: -0.1700

Data Index: 3823600 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0042. Min Act: -0.1700

Data Index: 3446046 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1224. Min Range: -3.1224

Max Act: 3.0048. Min Act: -0.1700

Data Index: 7758087 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9990. Min Act: -0.1700

Data Index: 3976582 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9889. Min Act: -0.1700

Data Index: 8466340 (Open Web Text)

Max Activating Token Index: 825

Text #9

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9721. Min Act: -0.1700

Data Index: 3794606 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9449. Min Act: -0.1700

Data Index: 7136266 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9370. Min Act: -0.1700

Data Index: 8183153 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9780. Min Act: -0.1700

Data Index: 3180206 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9369. Min Act: -0.1700

Data Index: 5453297 (Open Web Text)

Max Activating Token Index: 256

Text #14

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9331. Min Act: -0.1700

Data Index: 7058057 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9527. Min Act: -0.1700

Data Index: 5817731 (Open Web Text)

Max Activating Token Index: 214

Text #16

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9235. Min Act: -0.1700

Data Index: 1457624 (Open Web Text)

Max Activating Token Index: 245

Text #17

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9035. Min Act: -0.1700

Data Index: 473868 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9350. Min Act: -0.1700

Data Index: 7578111 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.1224. Min Range: -3.1224

Max Act: 2.9153. Min Act: -0.1700

Data Index: 5508481 (Open Web Text)

Max Activating Token Index: 479