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

Dataset: Open Web Text

Neuron 2306 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: 4.0835. Min Range: -4.0835

Max Act: 4.0834. Min Act: -0.1700

Data Index: 866152 (Open Web Text)

Max Activating Token Index: 755

Text #1

Max Range: 4.0835. Min Range: -4.0835

Max Act: 4.0600. Min Act: -0.1700

Data Index: 6966518 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 4.0835. Min Range: -4.0835

Max Act: 4.0835. Min Act: -0.1700

Data Index: 8277430 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 4.0835. Min Range: -4.0835

Max Act: 4.0088. Min Act: -0.1700

Data Index: 8691504 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.9873. Min Act: -0.1700

Data Index: 1039315 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1587669 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8997. Min Act: -0.1700

Data Index: 747822 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8921. Min Act: -0.1700

Data Index: 186948 (Open Web Text)

Max Activating Token Index: 689

Text #8

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8699. Min Act: -0.1700

Data Index: 5942045 (Open Web Text)

Max Activating Token Index: 605

Text #9

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8890. Min Act: -0.1700

Data Index: 1383523 (Open Web Text)

Max Activating Token Index: 398

Text #10

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8314. Min Act: -0.1700

Data Index: 8707901 (Open Web Text)

Max Activating Token Index: 519

Text #11

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8254. Min Act: -0.1700

Data Index: 2893973 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8160. Min Act: -0.1700

Data Index: 5991742 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8338. Min Act: -0.1700

Data Index: 5159448 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8215. Min Act: -0.1700

Data Index: 5757141 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8054. Min Act: -0.1700

Data Index: 4629050 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8033. Min Act: -0.1700

Data Index: 6975611 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.7981. Min Act: -0.1700

Data Index: 4629053 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.8154. Min Act: -0.1700

Data Index: 3932069 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 4.0835. Min Range: -4.0835

Max Act: 3.7882. Min Act: -0.1700

Data Index: 3410366 (Open Web Text)

Max Activating Token Index: 623