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

Dataset: Open Web Text

Neuron 1492 in Layer 1

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: 4.5370. Min Range: -4.5370

Max Act: 4.5370. Min Act: -0.1700

Data Index: 371500 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.5144. Min Act: -0.1700

Data Index: 743405 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.4987. Min Act: -0.1700

Data Index: 7796377 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.4056. Min Act: -0.1700

Data Index: 259651 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.4045. Min Act: -0.1700

Data Index: 786943 (Open Web Text)

Max Activating Token Index: 566

Text #5

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.4114. Min Act: -0.1700

Data Index: 1492349 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.4052. Min Act: -0.1700

Data Index: 6227575 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3898. Min Act: -0.1700

Data Index: 5921586 (Open Web Text)

Max Activating Token Index: 578

Text #8

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3765. Min Act: -0.1700

Data Index: 2485631 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3547. Min Act: -0.1700

Data Index: 8161711 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3547. Min Act: -0.1700

Data Index: 8265156 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3414. Min Act: -0.1700

Data Index: 7634647 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3421. Min Act: -0.1700

Data Index: 5827509 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3537. Min Act: -0.1700

Data Index: 681870 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3547. Min Act: -0.1700

Data Index: 5018502 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3547. Min Act: -0.1700

Data Index: 7754051 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3207. Min Act: -0.1700

Data Index: 2857463 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3263. Min Act: -0.1700

Data Index: 243867 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3398. Min Act: -0.1700

Data Index: 5128875 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.5370. Min Range: -4.5370

Max Act: 4.3129. Min Act: -0.1700

Data Index: 5242842 (Open Web Text)

Max Activating Token Index: 336