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

Dataset: Open Web Text

Neuron 220 in Layer 3

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: 3.1239. Min Range: -3.1239

Max Act: 3.1239. Min Act: -0.1700

Data Index: 6536348 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.1239. Min Range: -3.1239

Max Act: 3.0124. Min Act: -0.1700

Data Index: 2433636 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 3.1239. Min Range: -3.1239

Max Act: 3.0191. Min Act: -0.1700

Data Index: 946321 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.9811. Min Act: -0.1700

Data Index: 4129273 (Open Web Text)

Max Activating Token Index: 710

Text #4

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.9297. Min Act: -0.1700

Data Index: 4524836 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.9049. Min Act: -0.1700

Data Index: 7938308 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8932. Min Act: -0.1700

Data Index: 6685394 (Open Web Text)

Max Activating Token Index: 754

Text #7

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8565. Min Act: -0.1700

Data Index: 913059 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8612. Min Act: -0.1700

Data Index: 6685395 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8372. Min Act: -0.1700

Data Index: 5052930 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8304. Min Act: -0.1700

Data Index: 7973888 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8267. Min Act: -0.1700

Data Index: 8778849 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8183. Min Act: -0.1700

Data Index: 5849869 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1096387 (Open Web Text)

Max Activating Token Index: 691

Text #14

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8500. Min Act: -0.1700

Data Index: 3576280 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8235. Min Act: -0.1700

Data Index: 6670962 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8195. Min Act: -0.1700

Data Index: 278211 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8268. Min Act: -0.1700

Data Index: 521401 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8098. Min Act: -0.1700

Data Index: 5807499 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 3.1239. Min Range: -3.1239

Max Act: 2.8314. Min Act: -0.1700

Data Index: 7056109 (Open Web Text)

Max Activating Token Index: 168