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

Dataset: Open Web Text

Neuron 196 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: 1.4472. Min Range: -1.4472

Max Act: 1.4472. Min Act: -0.1700

Data Index: 8447553 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4208. Min Act: -0.1700

Data Index: 4233278 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4117. Min Act: -0.1699

Data Index: 2504399 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3974. Min Act: -0.1696

Data Index: 3113320 (Open Web Text)

Max Activating Token Index: 650

Text #4

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3888. Min Act: -0.1700

Data Index: 4373913 (Open Web Text)

Max Activating Token Index: 856

Text #5

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3966. Min Act: -0.1674

Data Index: 5965163 (Open Web Text)

Max Activating Token Index: 103

Text #6

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.4042. Min Act: -0.1700

Data Index: 6318542 (Open Web Text)

Max Activating Token Index: 972

Text #7

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3938. Min Act: -0.1700

Data Index: 1654570 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3884. Min Act: -0.1700

Data Index: 672928 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3812. Min Act: -0.1700

Data Index: 8029257 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3847. Min Act: -0.1700

Data Index: 4457475 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3859. Min Act: -0.1700

Data Index: 2125786 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3815. Min Act: -0.1700

Data Index: 5776725 (Open Web Text)

Max Activating Token Index: 987

Text #13

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3702. Min Act: -0.1699

Data Index: 3586782 (Open Web Text)

Max Activating Token Index: 962

Text #14

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3648. Min Act: -0.1700

Data Index: 1648308 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3697. Min Act: -0.1700

Data Index: 5568329 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3636. Min Act: -0.1700

Data Index: 4718378 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3647. Min Act: -0.1700

Data Index: 930762 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3691. Min Act: -0.1700

Data Index: 3288958 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 1.4472. Min Range: -1.4472

Max Act: 1.3545. Min Act: -0.1700

Data Index: 2739975 (Open Web Text)

Max Activating Token Index: 987