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

Dataset: Open Web Text

Neuron 1718 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: 5.6670. Min Range: -5.6670

Max Act: 5.6566. Min Act: -0.1700

Data Index: 8013295 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.6670. Min Act: -0.1700

Data Index: 486863 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.6148. Min Act: -0.1700

Data Index: 1481289 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.6098. Min Act: -0.1700

Data Index: 8128126 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5833. Min Act: -0.1700

Data Index: 3759486 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5874. Min Act: -0.1700

Data Index: 8401378 (Open Web Text)

Max Activating Token Index: 686

Text #6

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5636. Min Act: -0.1700

Data Index: 2502090 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5685. Min Act: -0.1700

Data Index: 3902812 (Open Web Text)

Max Activating Token Index: 822

Text #8

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5379. Min Act: -0.1700

Data Index: 2090378 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5250. Min Act: -0.1700

Data Index: 542309 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5111. Min Act: -0.1700

Data Index: 2789018 (Open Web Text)

Max Activating Token Index: 982

Text #11

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5032. Min Act: -0.1700

Data Index: 6192776 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5454. Min Act: -0.1700

Data Index: 2065129 (Open Web Text)

Max Activating Token Index: 779

Text #13

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.4983. Min Act: -0.1700

Data Index: 864262 (Open Web Text)

Max Activating Token Index: 950

Text #14

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5258. Min Act: -0.1700

Data Index: 560045 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5000. Min Act: -0.1700

Data Index: 6381162 (Open Web Text)

Max Activating Token Index: 230

Text #16

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5378. Min Act: -0.1700

Data Index: 6298765 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.4966. Min Act: -0.1700

Data Index: 1286478 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.4935. Min Act: -0.1700

Data Index: 8372684 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 5.6670. Min Range: -5.6670

Max Act: 5.5141. Min Act: -0.1700

Data Index: 7316099 (Open Web Text)

Max Activating Token Index: 289