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

Dataset: Open Web Text

Neuron 3065 in Layer 5

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: 3.2563. Min Range: -3.2563

Max Act: 3.2563. Min Act: -0.1700

Data Index: 3697806 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.1210. Min Act: -0.1700

Data Index: 3976436 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.1470. Min Act: -0.1700

Data Index: 4626158 (Open Web Text)

Max Activating Token Index: 781

Text #3

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0345. Min Act: -0.1700

Data Index: 4547580 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0595. Min Act: -0.1700

Data Index: 3389462 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0249. Min Act: -0.1700

Data Index: 436591 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0450. Min Act: -0.1700

Data Index: 7916920 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0390. Min Act: -0.1700

Data Index: 3813647 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1227563 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0159. Min Act: -0.1700

Data Index: 8139494 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0545. Min Act: -0.1700

Data Index: 8245296 (Open Web Text)

Max Activating Token Index: 793

Text #11

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0162. Min Act: -0.1700

Data Index: 8723405 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 3.2563. Min Range: -3.2563

Max Act: 2.9940. Min Act: -0.1700

Data Index: 2811124 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0038. Min Act: -0.1700

Data Index: 3110718 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 3.2563. Min Range: -3.2563

Max Act: 2.9839. Min Act: -0.1700

Data Index: 4468357 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 3.2563. Min Range: -3.2563

Max Act: 2.9932. Min Act: -0.1700

Data Index: 3005251 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0099. Min Act: -0.1700

Data Index: 7328904 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 3.2563. Min Range: -3.2563

Max Act: 3.0191. Min Act: -0.1700

Data Index: 5351339 (Open Web Text)

Max Activating Token Index: 941

Text #18

Max Range: 3.2563. Min Range: -3.2563

Max Act: 2.9657. Min Act: -0.1700

Data Index: 2942954 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 3.2563. Min Range: -3.2563

Max Act: 2.9553. Min Act: -0.1700

Data Index: 864148 (Open Web Text)

Max Activating Token Index: 224