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

Dataset: Open Web Text

Neuron 827 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: 4.0028. Min Range: -4.0028

Max Act: 4.0028. Min Act: -0.1683

Data Index: 6153126 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.9733. Min Act: -0.1662

Data Index: 4492735 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.9258. Min Act: -0.1700

Data Index: 3907385 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.9087. Min Act: -0.1700

Data Index: 4924328 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8807. Min Act: -0.1700

Data Index: 3513777 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8323. Min Act: -0.1700

Data Index: 4454619 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8318. Min Act: -0.1697

Data Index: 6643834 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8066. Min Act: -0.1680

Data Index: 1610121 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.7947. Min Act: -0.1657

Data Index: 6153140 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8039. Min Act: -0.1700

Data Index: 5168206 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8242. Min Act: -0.1691

Data Index: 6153120 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8081. Min Act: -0.1700

Data Index: 1844884 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8244. Min Act: -0.1695

Data Index: 3203547 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8114. Min Act: -0.1700

Data Index: 4085088 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8071. Min Act: -0.1700

Data Index: 526594 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8334. Min Act: -0.1700

Data Index: 8024139 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8249. Min Act: -0.1629

Data Index: 5986213 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.8057. Min Act: -0.1700

Data Index: 4816961 (Open Web Text)

Max Activating Token Index: 486

Text #18

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.7676. Min Act: -0.1700

Data Index: 5556896 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 4.0028. Min Range: -4.0028

Max Act: 3.7730. Min Act: -0.1663

Data Index: 5645731 (Open Web Text)

Max Activating Token Index: 66