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

Dataset: Open Web Text

Neuron 2099 in Layer 6

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: 3.5045. Min Range: -3.5045

Max Act: 3.5045. Min Act: -0.1700

Data Index: 1776119 (Open Web Text)

Max Activating Token Index: 691

Text #1

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.4418. Min Act: -0.1700

Data Index: 5783638 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.4190. Min Act: -0.1700

Data Index: 2891958 (Open Web Text)

Max Activating Token Index: 953

Text #3

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.4062. Min Act: -0.1700

Data Index: 855913 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3708. Min Act: -0.1700

Data Index: 5712424 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3614. Min Act: -0.1700

Data Index: 3033171 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3688. Min Act: -0.1700

Data Index: 1568075 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3784. Min Act: -0.1700

Data Index: 762160 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3595. Min Act: -0.1700

Data Index: 5854669 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3513. Min Act: -0.1700

Data Index: 93925 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3371. Min Act: -0.1700

Data Index: 3418025 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3221. Min Act: -0.1700

Data Index: 6494244 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2989. Min Act: -0.1700

Data Index: 243740 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3361. Min Act: -0.1700

Data Index: 3427267 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3187. Min Act: -0.1700

Data Index: 4933664 (Open Web Text)

Max Activating Token Index: 569

Text #15

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3320. Min Act: -0.1700

Data Index: 1133493 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3010. Min Act: -0.1700

Data Index: 777860 (Open Web Text)

Max Activating Token Index: 939

Text #17

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1611371 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.2893. Min Act: -0.1700

Data Index: 2363310 (Open Web Text)

Max Activating Token Index: 737

Text #19

Max Range: 3.5045. Min Range: -3.5045

Max Act: 3.3006. Min Act: -0.1700

Data Index: 5891101 (Open Web Text)

Max Activating Token Index: 1002