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

Dataset: Open Web Text

Neuron 669 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: 1.8673. Min Range: -1.8673

Max Act: 1.8673. Min Act: -0.1700

Data Index: 6242923 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8514. Min Act: -0.1700

Data Index: 3789501 (Open Web Text)

Max Activating Token Index: 156

Text #2

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8420. Min Act: -0.1700

Data Index: 4345690 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8313. Min Act: -0.1700

Data Index: 153072 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8368. Min Act: -0.1700

Data Index: 6781547 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8132. Min Act: -0.1700

Data Index: 294116 (Open Web Text)

Max Activating Token Index: 88

Text #6

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8279. Min Act: -0.1700

Data Index: 2897947 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8106. Min Act: -0.1700

Data Index: 7313977 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7991. Min Act: -0.1700

Data Index: 2211417 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7961. Min Act: -0.1700

Data Index: 1840244 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7912. Min Act: -0.1700

Data Index: 2529775 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7963. Min Act: -0.1700

Data Index: 2899421 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7899. Min Act: -0.1700

Data Index: 5671825 (Open Web Text)

Max Activating Token Index: 310

Text #13

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7920. Min Act: -0.1700

Data Index: 5820549 (Open Web Text)

Max Activating Token Index: 609

Text #14

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7806. Min Act: -0.1700

Data Index: 7849643 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7771. Min Act: -0.1699

Data Index: 383513 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7822. Min Act: -0.1698

Data Index: 529058 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7853. Min Act: -0.1700

Data Index: 7931532 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7807. Min Act: -0.1698

Data Index: 3694666 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7861. Min Act: -0.1689

Data Index: 5374645 (Open Web Text)

Max Activating Token Index: 15