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

Dataset: Open Web Text

Neuron 1673 in Layer 0

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: 5.5554. Min Range: -5.5554

Max Act: 5.5554. Min Act: -0.1700

Data Index: 1505847 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.5554. Min Act: -0.1700

Data Index: 4073085 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.5098. Min Act: -0.1700

Data Index: 5345155 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.4694. Min Act: -0.1700

Data Index: 1505852 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.4701. Min Act: -0.1700

Data Index: 4093369 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3942. Min Act: -0.1700

Data Index: 7746812 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3603. Min Act: -0.1700

Data Index: 2151522 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3506. Min Act: -0.1700

Data Index: 8766293 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3506. Min Act: -0.1700

Data Index: 5372514 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3506. Min Act: -0.1700

Data Index: 5325100 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.3173. Min Act: -0.1700

Data Index: 6272528 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.2269. Min Act: -0.1700

Data Index: 4456680 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.2140. Min Act: -0.1700

Data Index: 1505849 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.1814. Min Act: -0.1700

Data Index: 8029300 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.1743. Min Act: -0.1700

Data Index: 2116629 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.1814. Min Act: -0.1700

Data Index: 358749 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.1414. Min Act: -0.1700

Data Index: 182205 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.1483. Min Act: -0.1700

Data Index: 4912048 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.0518. Min Act: -0.1700

Data Index: 6098732 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.5554. Min Range: -5.5554

Max Act: 5.0288. Min Act: -0.1700

Data Index: 6024077 (Open Web Text)

Max Activating Token Index: 3