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

Dataset: Open Web Text

Neuron 650 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: 3.1327. Min Range: -3.1327

Max Act: 3.1327. Min Act: -0.1700

Data Index: 1371498 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0715. Min Act: -0.1700

Data Index: 4546348 (Open Web Text)

Max Activating Token Index: 523

Text #2

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0762. Min Act: -0.1700

Data Index: 8471612 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0740. Min Act: -0.1700

Data Index: 3696123 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0434. Min Act: -0.1700

Data Index: 7233922 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0164. Min Act: -0.1700

Data Index: 4928340 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0281. Min Act: -0.1700

Data Index: 4770314 (Open Web Text)

Max Activating Token Index: 716

Text #7

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0101. Min Act: -0.1700

Data Index: 2215579 (Open Web Text)

Max Activating Token Index: 168

Text #8

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0228. Min Act: -0.1700

Data Index: 57776 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9954. Min Act: -0.1700

Data Index: 5204084 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9818. Min Act: -0.1700

Data Index: 4663694 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9939. Min Act: -0.1700

Data Index: 4488308 (Open Web Text)

Max Activating Token Index: 164

Text #12

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0074. Min Act: -0.1700

Data Index: 6390319 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.0127. Min Act: -0.1700

Data Index: 2647126 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9722. Min Act: -0.1700

Data Index: 7950291 (Open Web Text)

Max Activating Token Index: 205

Text #15

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9805. Min Act: -0.1700

Data Index: 2667912 (Open Web Text)

Max Activating Token Index: 1009

Text #16

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9807. Min Act: -0.1700

Data Index: 69515 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9756. Min Act: -0.1700

Data Index: 1630401 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9585. Min Act: -0.1700

Data Index: 5313579 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.9474. Min Act: -0.1700

Data Index: 3628758 (Open Web Text)

Max Activating Token Index: 482