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

Dataset: Open Web Text

Neuron 1898 in Layer 0

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: 2.0004. Min Range: -2.0004

Max Act: 2.0004. Min Act: -0.1700

Data Index: 7036700 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9525. Min Act: -0.1700

Data Index: 5358472 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9582. Min Act: -0.1698

Data Index: 2754725 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9249. Min Act: -0.1700

Data Index: 7772528 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9512. Min Act: -0.1700

Data Index: 8360525 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9509. Min Act: -0.1514

Data Index: 8003780 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9399. Min Act: -0.1699

Data Index: 1351038 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9266. Min Act: -0.1700

Data Index: 6367788 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9211. Min Act: -0.1700

Data Index: 2839656 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9186. Min Act: -0.1700

Data Index: 629899 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9117. Min Act: -0.1700

Data Index: 3687972 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9125. Min Act: -0.1700

Data Index: 8785929 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.9125. Min Act: -0.1700

Data Index: 1154809 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8918. Min Act: -0.1700

Data Index: 3207833 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8828. Min Act: -0.1700

Data Index: 2126034 (Open Web Text)

Max Activating Token Index: 843

Text #15

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8980. Min Act: -0.1700

Data Index: 988731 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8967. Min Act: -0.1700

Data Index: 2949953 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8715. Min Act: -0.1700

Data Index: 584097 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8808. Min Act: -0.1700

Data Index: 3368520 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.0004. Min Range: -2.0004

Max Act: 1.8773. Min Act: -0.1699

Data Index: 1723830 (Open Web Text)

Max Activating Token Index: 460