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

Dataset: Open Web Text

Neuron 2352 in Layer 5

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: 5.5277. Min Range: -5.5277

Max Act: 5.5277. Min Act: -0.1700

Data Index: 5038897 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3472. Min Act: -0.1700

Data Index: 8248347 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3375. Min Act: -0.1700

Data Index: 202045 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3164. Min Act: -0.1700

Data Index: 7863330 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2781. Min Act: -0.1700

Data Index: 7424181 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2758. Min Act: -0.1700

Data Index: 5167293 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2618. Min Act: -0.1700

Data Index: 1012124 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2092. Min Act: -0.1700

Data Index: 2604317 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2522. Min Act: -0.1700

Data Index: 6841702 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2200. Min Act: -0.1700

Data Index: 1718787 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1967. Min Act: -0.1700

Data Index: 4040469 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2153. Min Act: -0.1700

Data Index: 416319 (Open Web Text)

Max Activating Token Index: 702

Text #12

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1979. Min Act: -0.1700

Data Index: 7745879 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2030. Min Act: -0.1700

Data Index: 7327159 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2047. Min Act: -0.1700

Data Index: 8091478 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1944. Min Act: -0.1700

Data Index: 2688155 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1837. Min Act: -0.1700

Data Index: 5727744 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1431. Min Act: -0.1700

Data Index: 3374759 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1490. Min Act: -0.1700

Data Index: 74167 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.1756. Min Act: -0.1700

Data Index: 7458509 (Open Web Text)

Max Activating Token Index: 898