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

Dataset: Open Web Text

Neuron 2975 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: 5.0062. Min Range: -5.0062

Max Act: 5.0062. Min Act: -0.1700

Data Index: 1213402 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8735. Min Act: -0.1700

Data Index: 8739148 (Open Web Text)

Max Activating Token Index: 943

Text #2

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8894. Min Act: -0.1700

Data Index: 4362300 (Open Web Text)

Max Activating Token Index: 695

Text #3

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8800. Min Act: -0.1700

Data Index: 2299998 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8215. Min Act: -0.1700

Data Index: 7410122 (Open Web Text)

Max Activating Token Index: 507

Text #5

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8447. Min Act: -0.1700

Data Index: 3493561 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8341. Min Act: -0.1700

Data Index: 18897 (Open Web Text)

Max Activating Token Index: 474

Text #7

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8254. Min Act: -0.1700

Data Index: 5673154 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8008. Min Act: -0.1700

Data Index: 8423781 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8405. Min Act: -0.1700

Data Index: 6038696 (Open Web Text)

Max Activating Token Index: 958

Text #10

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8427. Min Act: -0.1700

Data Index: 1295955 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8561. Min Act: -0.1700

Data Index: 2655060 (Open Web Text)

Max Activating Token Index: 270

Text #12

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8069. Min Act: -0.1700

Data Index: 650080 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8034. Min Act: -0.1700

Data Index: 3951245 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.7929. Min Act: -0.1700

Data Index: 1785698 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.7983. Min Act: -0.1700

Data Index: 7340904 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.8367. Min Act: -0.1700

Data Index: 2729455 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.7971. Min Act: -0.1700

Data Index: 8719599 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.7699. Min Act: -0.1700

Data Index: 464174 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 5.0062. Min Range: -5.0062

Max Act: 4.7581. Min Act: -0.1700

Data Index: 1935256 (Open Web Text)

Max Activating Token Index: 835