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

Dataset: Open Web Text

Neuron 85 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: 3.3477. Min Range: -3.3477

Max Act: 3.3477. Min Act: -0.1700

Data Index: 3888679 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2653. Min Act: -0.1700

Data Index: 3471453 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.2118. Min Act: -0.1700

Data Index: 1491240 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1556. Min Act: -0.1700

Data Index: 1710009 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1561. Min Act: -0.1700

Data Index: 2458767 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1467. Min Act: -0.1700

Data Index: 229280 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1227. Min Act: -0.1700

Data Index: 1954956 (Open Web Text)

Max Activating Token Index: 404

Text #7

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1003. Min Act: -0.1700

Data Index: 721658 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1222. Min Act: -0.1700

Data Index: 5271830 (Open Web Text)

Max Activating Token Index: 620

Text #9

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.1183. Min Act: -0.1700

Data Index: 976519 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0717. Min Act: -0.1700

Data Index: 2373816 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0638. Min Act: -0.1700

Data Index: 376796 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0779. Min Act: -0.1700

Data Index: 5512695 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0857. Min Act: -0.1700

Data Index: 2687322 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0718. Min Act: -0.1700

Data Index: 243765 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0758. Min Act: -0.1700

Data Index: 709199 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0473. Min Act: -0.1700

Data Index: 4279583 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0547. Min Act: -0.1700

Data Index: 4298635 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0529. Min Act: -0.1700

Data Index: 4328076 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 3.3477. Min Range: -3.3477

Max Act: 3.0728. Min Act: -0.1700

Data Index: 5021949 (Open Web Text)

Max Activating Token Index: 176