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

Dataset: Open Web Text

Neuron 809 in Layer 6

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: 4.2593. Min Range: -4.2593

Max Act: 4.2593. Min Act: -0.1700

Data Index: 7430800 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.1852. Min Act: -0.1700

Data Index: 6267146 (Open Web Text)

Max Activating Token Index: 792

Text #2

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.1755. Min Act: -0.1700

Data Index: 6883326 (Open Web Text)

Max Activating Token Index: 609

Text #3

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.1422. Min Act: -0.1700

Data Index: 6805561 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.1036. Min Act: -0.1700

Data Index: 7227174 (Open Web Text)

Max Activating Token Index: 139

Text #5

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0991. Min Act: -0.1700

Data Index: 3455074 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0725. Min Act: -0.1700

Data Index: 2874812 (Open Web Text)

Max Activating Token Index: 116

Text #7

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0291. Min Act: -0.1700

Data Index: 2098562 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0332. Min Act: -0.1700

Data Index: 347687 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0169. Min Act: -0.1700

Data Index: 4795489 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0215. Min Act: -0.1700

Data Index: 1272378 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0450. Min Act: -0.1700

Data Index: 1838621 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0494. Min Act: -0.1700

Data Index: 2669459 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0265. Min Act: -0.1700

Data Index: 1155971 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 4.2593. Min Range: -4.2593

Max Act: 3.9828. Min Act: -0.1700

Data Index: 7593348 (Open Web Text)

Max Activating Token Index: 602

Text #15

Max Range: 4.2593. Min Range: -4.2593

Max Act: 3.9750. Min Act: -0.1700

Data Index: 4600016 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 4.2593. Min Range: -4.2593

Max Act: 4.0182. Min Act: -0.1700

Data Index: 7832814 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 4.2593. Min Range: -4.2593

Max Act: 3.9963. Min Act: -0.1700

Data Index: 4954892 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 4.2593. Min Range: -4.2593

Max Act: 3.9645. Min Act: -0.1700

Data Index: 4836224 (Open Web Text)

Max Activating Token Index: 784

Text #19

Max Range: 4.2593. Min Range: -4.2593

Max Act: 3.9905. Min Act: -0.1700

Data Index: 1887393 (Open Web Text)

Max Activating Token Index: 562