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

Dataset: Open Web Text

Neuron 1786 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: 5.3826. Min Range: -5.3826

Max Act: 5.3657. Min Act: -0.1700

Data Index: 7239372 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3533. Min Act: -0.1700

Data Index: 7868110 (Open Web Text)

Max Activating Token Index: 235

Text #2

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3544. Min Act: -0.1700

Data Index: 4045438 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3826. Min Act: -0.1700

Data Index: 7694393 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3279. Min Act: -0.1700

Data Index: 6437291 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3231. Min Act: -0.1700

Data Index: 4542608 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3081. Min Act: -0.1700

Data Index: 3002773 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2945. Min Act: -0.1700

Data Index: 8810620 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2753. Min Act: -0.1700

Data Index: 1290060 (Open Web Text)

Max Activating Token Index: 566

Text #9

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3052. Min Act: -0.1700

Data Index: 4074651 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2722. Min Act: -0.1700

Data Index: 8268154 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3402. Min Act: -0.1700

Data Index: 3087414 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2709. Min Act: -0.1700

Data Index: 7575811 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2574. Min Act: -0.1700

Data Index: 6102695 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2598. Min Act: -0.1700

Data Index: 4110789 (Open Web Text)

Max Activating Token Index: 314

Text #15

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2699. Min Act: -0.1700

Data Index: 4361181 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2839. Min Act: -0.1700

Data Index: 5608601 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2621. Min Act: -0.1700

Data Index: 1746872 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2848. Min Act: -0.1700

Data Index: 320010 (Open Web Text)

Max Activating Token Index: 434

Text #19

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.2573. Min Act: -0.1700

Data Index: 3501388 (Open Web Text)

Max Activating Token Index: 965