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

Dataset: Open Web Text

Neuron 2607 in Layer 3

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: 1.9036. Min Range: -1.9036

Max Act: 1.9036. Min Act: -0.1700

Data Index: 4753684 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.8966. Min Act: -0.1700

Data Index: 5702264 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.8260. Min Act: -0.1700

Data Index: 8353114 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.8368. Min Act: -0.1700

Data Index: 1344955 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.8081. Min Act: -0.1700

Data Index: 5423715 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7831. Min Act: -0.1700

Data Index: 4340418 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7660. Min Act: -0.1700

Data Index: 5289767 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7825. Min Act: -0.1700

Data Index: 1915956 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7767. Min Act: -0.1700

Data Index: 3475617 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7607. Min Act: -0.1700

Data Index: 1904728 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7532. Min Act: -0.1700

Data Index: 2634352 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7644. Min Act: -0.1700

Data Index: 4840913 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7435. Min Act: -0.1700

Data Index: 2092061 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7429. Min Act: -0.1700

Data Index: 7622135 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7531. Min Act: -0.1700

Data Index: 1524820 (Open Web Text)

Max Activating Token Index: 66

Text #15

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7370. Min Act: -0.1700

Data Index: 3473400 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7305. Min Act: -0.1700

Data Index: 2591839 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7306. Min Act: -0.1700

Data Index: 2982203 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7307. Min Act: -0.1700

Data Index: 5018808 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.7452. Min Act: -0.1700

Data Index: 5060533 (Open Web Text)

Max Activating Token Index: 81