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

Dataset: Open Web Text

Neuron 296 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: 5.5559. Min Range: -5.5559

Max Act: 5.5559. Min Act: -0.1700

Data Index: 7508378 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4508. Min Act: -0.1700

Data Index: 6045438 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4809. Min Act: -0.1700

Data Index: 6507438 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4128. Min Act: -0.1700

Data Index: 4693864 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4234. Min Act: -0.1700

Data Index: 5189402 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4174. Min Act: -0.1700

Data Index: 8667475 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3843. Min Act: -0.1700

Data Index: 7777960 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3961. Min Act: -0.1700

Data Index: 5759152 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3991. Min Act: -0.1700

Data Index: 797766 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4111. Min Act: -0.1700

Data Index: 1043331 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4121. Min Act: -0.1700

Data Index: 8534431 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.4029. Min Act: -0.1700

Data Index: 4492057 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3896. Min Act: -0.1700

Data Index: 5277013 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3932. Min Act: -0.1700

Data Index: 2488132 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3770. Min Act: -0.1700

Data Index: 7436459 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3978. Min Act: -0.1700

Data Index: 1853999 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3759. Min Act: -0.1700

Data Index: 3081519 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3606. Min Act: -0.1700

Data Index: 1343168 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3668. Min Act: -0.1700

Data Index: 5514858 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.5559. Min Range: -5.5559

Max Act: 5.3854. Min Act: -0.1700

Data Index: 1039483 (Open Web Text)

Max Activating Token Index: 6