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

Dataset: Open Web Text

Neuron 1287 in Layer 4

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: 4.3384. Min Range: -4.3384

Max Act: 4.3384. Min Act: -0.1700

Data Index: 6190017 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1650. Min Act: -0.1700

Data Index: 3530235 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2036. Min Act: -0.1700

Data Index: 4806417 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1909. Min Act: -0.1700

Data Index: 4214421 (Open Web Text)

Max Activating Token Index: 746

Text #4

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1749. Min Act: -0.1700

Data Index: 4028923 (Open Web Text)

Max Activating Token Index: 739

Text #5

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1988. Min Act: -0.1700

Data Index: 432142 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1986. Min Act: -0.1700

Data Index: 2222571 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1924. Min Act: -0.1700

Data Index: 6617041 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.2092. Min Act: -0.1700

Data Index: 3594203 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1445. Min Act: -0.1700

Data Index: 1925834 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1496. Min Act: -0.1700

Data Index: 6245454 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1421. Min Act: -0.1700

Data Index: 8428460 (Open Web Text)

Max Activating Token Index: 628

Text #12

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1530. Min Act: -0.1700

Data Index: 8457302 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1482. Min Act: -0.1700

Data Index: 3594201 (Open Web Text)

Max Activating Token Index: 732

Text #14

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1630. Min Act: -0.1700

Data Index: 6326876 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1500. Min Act: -0.1700

Data Index: 1687568 (Open Web Text)

Max Activating Token Index: 328

Text #16

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1251. Min Act: -0.1700

Data Index: 607104 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1026. Min Act: -0.1700

Data Index: 3606954 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.0964. Min Act: -0.1700

Data Index: 6305296 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 4.3384. Min Range: -4.3384

Max Act: 4.1270. Min Act: -0.1700

Data Index: 5811201 (Open Web Text)

Max Activating Token Index: 830