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

Dataset: Open Web Text

Neuron 2135 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: 3.0999. Min Range: -3.0999

Max Act: 3.0999. Min Act: -0.1700

Data Index: 5594785 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 3.0999. Min Range: -3.0999

Max Act: 3.0508. Min Act: -0.1700

Data Index: 2255280 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 3.0999. Min Range: -3.0999

Max Act: 3.0325. Min Act: -0.1700

Data Index: 48036 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9742. Min Act: -0.1700

Data Index: 8339275 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9685. Min Act: -0.1700

Data Index: 1212361 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9327. Min Act: -0.1700

Data Index: 6017455 (Open Web Text)

Max Activating Token Index: 906

Text #6

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9384. Min Act: -0.1700

Data Index: 4345695 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9060. Min Act: -0.1700

Data Index: 1094051 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9343. Min Act: -0.1700

Data Index: 2954167 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9203. Min Act: -0.1700

Data Index: 7607616 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9169. Min Act: -0.1700

Data Index: 7966744 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9061. Min Act: -0.1700

Data Index: 1842781 (Open Web Text)

Max Activating Token Index: 848

Text #12

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8994. Min Act: -0.1700

Data Index: 7334474 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9025. Min Act: -0.1700

Data Index: 2715925 (Open Web Text)

Max Activating Token Index: 840

Text #14

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.9067. Min Act: -0.1700

Data Index: 4802715 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8985. Min Act: -0.1700

Data Index: 7903041 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8707. Min Act: -0.1700

Data Index: 2580898 (Open Web Text)

Max Activating Token Index: 527

Text #17

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8810. Min Act: -0.1700

Data Index: 7933193 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8774. Min Act: -0.1700

Data Index: 6309946 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 3.0999. Min Range: -3.0999

Max Act: 2.8607. Min Act: -0.1700

Data Index: 2724605 (Open Web Text)

Max Activating Token Index: 914