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

Dataset: Open Web Text

Neuron 2946 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: 4.6945. Min Range: -4.6945

Max Act: 4.6945. Min Act: -0.1700

Data Index: 5226519 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5702. Min Act: -0.1700

Data Index: 5720981 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5480. Min Act: -0.1700

Data Index: 1036204 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5666. Min Act: -0.1700

Data Index: 1367343 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5368. Min Act: -0.1700

Data Index: 4639385 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5574. Min Act: -0.1700

Data Index: 3647356 (Open Web Text)

Max Activating Token Index: 328

Text #6

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5464. Min Act: -0.1700

Data Index: 2445101 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.5416. Min Act: -0.1700

Data Index: 5793915 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4988. Min Act: -0.1700

Data Index: 2993666 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4304. Min Act: -0.1700

Data Index: 7707176 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4538. Min Act: -0.1700

Data Index: 8605317 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4755. Min Act: -0.1700

Data Index: 3408579 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4398. Min Act: -0.1700

Data Index: 3938146 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4258. Min Act: -0.1700

Data Index: 3963075 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4463. Min Act: -0.1700

Data Index: 2984493 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4242. Min Act: -0.1700

Data Index: 2458436 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4079. Min Act: -0.1700

Data Index: 768043 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.3985. Min Act: -0.1700

Data Index: 324159 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4110. Min Act: -0.1700

Data Index: 4845504 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.6945. Min Range: -4.6945

Max Act: 4.4167. Min Act: -0.1700

Data Index: 1141338 (Open Web Text)

Max Activating Token Index: 596