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

Dataset: Open Web Text

Neuron 2150 in Layer 1

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: 3.6831. Min Range: -3.6831

Max Act: 3.6831. Min Act: -0.1700

Data Index: 806976 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6515. Min Act: -0.1700

Data Index: 4726463 (Open Web Text)

Max Activating Token Index: 542

Text #2

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6741. Min Act: -0.1700

Data Index: 7018632 (Open Web Text)

Max Activating Token Index: 742

Text #3

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6527. Min Act: -0.1700

Data Index: 7971237 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6594. Min Act: -0.1700

Data Index: 2299347 (Open Web Text)

Max Activating Token Index: 259

Text #5

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6408. Min Act: -0.1700

Data Index: 5245678 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6346. Min Act: -0.1700

Data Index: 636288 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6162. Min Act: -0.1700

Data Index: 8592739 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6289. Min Act: -0.1700

Data Index: 193418 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6173. Min Act: -0.1700

Data Index: 6294397 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6122. Min Act: -0.1700

Data Index: 4353519 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6080. Min Act: -0.1700

Data Index: 4369791 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6229. Min Act: -0.1700

Data Index: 3619173 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6116. Min Act: -0.1700

Data Index: 7854147 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6122. Min Act: -0.1700

Data Index: 7929845 (Open Web Text)

Max Activating Token Index: 262

Text #15

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.6175. Min Act: -0.1700

Data Index: 4613874 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5957. Min Act: -0.1700

Data Index: 6048354 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5967. Min Act: -0.1700

Data Index: 3421716 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5972. Min Act: -0.1700

Data Index: 2234620 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.6831. Min Range: -3.6831

Max Act: 3.5980. Min Act: -0.1700

Data Index: 1669395 (Open Web Text)

Max Activating Token Index: 553