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

Dataset: Open Web Text

Neuron 1166 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: 1.9531. Min Range: -1.9531

Max Act: 1.9531. Min Act: -0.1700

Data Index: 4367203 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.9325. Min Act: -0.1700

Data Index: 7150615 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.9309. Min Act: -0.1700

Data Index: 1773216 (Open Web Text)

Max Activating Token Index: 114

Text #3

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.9165. Min Act: -0.1700

Data Index: 1572184 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8992. Min Act: -0.1700

Data Index: 3274583 (Open Web Text)

Max Activating Token Index: 670

Text #5

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8843. Min Act: -0.1700

Data Index: 7699744 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8708. Min Act: -0.1700

Data Index: 6932949 (Open Web Text)

Max Activating Token Index: 369

Text #7

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8595. Min Act: -0.1700

Data Index: 1043105 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8521. Min Act: -0.1700

Data Index: 5267175 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8710. Min Act: -0.1700

Data Index: 205972 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8572. Min Act: -0.1700

Data Index: 6856591 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8373. Min Act: -0.1700

Data Index: 8789893 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8473. Min Act: -0.1700

Data Index: 7065667 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8420. Min Act: -0.1700

Data Index: 7842404 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8344. Min Act: -0.1700

Data Index: 7577141 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8082. Min Act: -0.1700

Data Index: 7634232 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.7888. Min Act: -0.1700

Data Index: 8224228 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.7970. Min Act: -0.1700

Data Index: 3159987 (Open Web Text)

Max Activating Token Index: 976

Text #18

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8230. Min Act: -0.1700

Data Index: 7065666 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 1.9531. Min Range: -1.9531

Max Act: 1.8119. Min Act: -0.1700

Data Index: 4494180 (Open Web Text)

Max Activating Token Index: 273