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

Dataset: Open Web Text

Neuron 1948 in Layer 4

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: 3.0942. Min Range: -3.0942

Max Act: 3.0821. Min Act: -0.1700

Data Index: 3321261 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0942. Min Range: -3.0942

Max Act: 3.0942. Min Act: -0.1700

Data Index: 6661189 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0942. Min Range: -3.0942

Max Act: 3.0795. Min Act: -0.1700

Data Index: 6818988 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0942. Min Range: -3.0942

Max Act: 3.0194. Min Act: -0.1700

Data Index: 577905 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9974. Min Act: -0.1700

Data Index: 3078075 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9903. Min Act: -0.1700

Data Index: 418633 (Open Web Text)

Max Activating Token Index: 725

Text #6

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9640. Min Act: -0.1700

Data Index: 4036411 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9798. Min Act: -0.1700

Data Index: 4834288 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9639. Min Act: -0.1700

Data Index: 8313395 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9617. Min Act: -0.1700

Data Index: 8138609 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9755. Min Act: -0.1700

Data Index: 540768 (Open Web Text)

Max Activating Token Index: 1004

Text #11

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9771. Min Act: -0.1700

Data Index: 1007905 (Open Web Text)

Max Activating Token Index: 263

Text #12

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9716. Min Act: -0.1700

Data Index: 3618735 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9562. Min Act: -0.1700

Data Index: 3102845 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9644. Min Act: -0.1700

Data Index: 1280233 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9433. Min Act: -0.1700

Data Index: 4899559 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9630. Min Act: -0.1700

Data Index: 335845 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9399. Min Act: -0.1700

Data Index: 53337 (Open Web Text)

Max Activating Token Index: 1017

Text #18

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9720. Min Act: -0.1700

Data Index: 5426883 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 3.0942. Min Range: -3.0942

Max Act: 2.9507. Min Act: -0.1700

Data Index: 5830012 (Open Web Text)

Max Activating Token Index: 1020