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

Dataset: Open Web Text

Neuron 2866 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: 4.7285. Min Range: -4.7285

Max Act: 4.7254. Min Act: -0.1700

Data Index: 5652059 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6396. Min Act: -0.1700

Data Index: 534395 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6553. Min Act: -0.1700

Data Index: 4421922 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.7285. Min Act: -0.1700

Data Index: 3831883 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6258. Min Act: -0.1700

Data Index: 6701402 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6004. Min Act: -0.1700

Data Index: 180147 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6277. Min Act: -0.1700

Data Index: 594143 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6401. Min Act: -0.1700

Data Index: 666600 (Open Web Text)

Max Activating Token Index: 167

Text #8

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6075. Min Act: -0.1700

Data Index: 3736411 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5960. Min Act: -0.1700

Data Index: 2612382 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.6068. Min Act: -0.1700

Data Index: 3417576 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5747. Min Act: -0.1700

Data Index: 3463625 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5944. Min Act: -0.1700

Data Index: 1423384 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5841. Min Act: -0.1700

Data Index: 1899795 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5978. Min Act: -0.1700

Data Index: 6112582 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5762. Min Act: -0.1700

Data Index: 6015015 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5253. Min Act: -0.1700

Data Index: 7538352 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5704. Min Act: -0.1700

Data Index: 2404878 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5500. Min Act: -0.1700

Data Index: 470745 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.5883. Min Act: -0.1700

Data Index: 4933424 (Open Web Text)

Max Activating Token Index: 58