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

Dataset: Open Web Text

Neuron 964 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: 3.0112. Min Range: -3.0112

Max Act: 3.0112. Min Act: -0.1700

Data Index: 8489795 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9729. Min Act: -0.1700

Data Index: 2091062 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9706. Min Act: -0.1700

Data Index: 8395957 (Open Web Text)

Max Activating Token Index: 878

Text #3

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9227. Min Act: -0.1700

Data Index: 6743263 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9511. Min Act: -0.1700

Data Index: 6400562 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9298. Min Act: -0.1700

Data Index: 3995995 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9009. Min Act: -0.1700

Data Index: 728131 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9169. Min Act: -0.1700

Data Index: 2516414 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8944. Min Act: -0.1700

Data Index: 7036114 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8903. Min Act: -0.1700

Data Index: 7740735 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8895. Min Act: -0.1700

Data Index: 4636088 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8940. Min Act: -0.1700

Data Index: 2882203 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9225. Min Act: -0.1700

Data Index: 8661439 (Open Web Text)

Max Activating Token Index: 425

Text #13

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9090. Min Act: -0.1700

Data Index: 3448151 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9067. Min Act: -0.1700

Data Index: 2347723 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8654. Min Act: -0.1700

Data Index: 3256198 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8829. Min Act: -0.1700

Data Index: 8284480 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8689. Min Act: -0.1700

Data Index: 617086 (Open Web Text)

Max Activating Token Index: 589

Text #18

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8714. Min Act: -0.1700

Data Index: 6705291 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8873. Min Act: -0.1700

Data Index: 3361942 (Open Web Text)

Max Activating Token Index: 798