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

Dataset: Open Web Text

Neuron 1419 in Layer 6

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: 4.7681. Min Range: -4.7681

Max Act: 4.7681. Min Act: -0.1700

Data Index: 5879494 (Open Web Text)

Max Activating Token Index: 832

Text #1

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.7491. Min Act: -0.1700

Data Index: 938096 (Open Web Text)

Max Activating Token Index: 236

Text #2

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6661. Min Act: -0.1700

Data Index: 2186647 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6726. Min Act: -0.1700

Data Index: 2017217 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6709. Min Act: -0.1700

Data Index: 8333925 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.7255. Min Act: -0.1700

Data Index: 2737510 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6895. Min Act: -0.1700

Data Index: 8522992 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6664. Min Act: -0.1700

Data Index: 8691926 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6504. Min Act: -0.1700

Data Index: 5515289 (Open Web Text)

Max Activating Token Index: 131

Text #9

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6272. Min Act: -0.1700

Data Index: 834733 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5994. Min Act: -0.1700

Data Index: 6871500 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5708. Min Act: -0.1700

Data Index: 6604696 (Open Web Text)

Max Activating Token Index: 885

Text #12

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.6014. Min Act: -0.1700

Data Index: 1910589 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5972. Min Act: -0.1700

Data Index: 7531875 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5227. Min Act: -0.1700

Data Index: 515487 (Open Web Text)

Max Activating Token Index: 859

Text #15

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5740. Min Act: -0.1700

Data Index: 498438 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5560. Min Act: -0.1700

Data Index: 6166539 (Open Web Text)

Max Activating Token Index: 883

Text #17

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5852. Min Act: -0.1700

Data Index: 5983987 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5750. Min Act: -0.1700

Data Index: 7348181 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 4.7681. Min Range: -4.7681

Max Act: 4.5811. Min Act: -0.1700

Data Index: 2192292 (Open Web Text)

Max Activating Token Index: 469