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

Dataset: Open Web Text

Neuron 1814 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: 6.1903. Min Range: -6.1903

Max Act: 6.1903. Min Act: -0.1700

Data Index: 3734145 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.8960. Min Act: -0.1700

Data Index: 3963435 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.8542. Min Act: -0.1700

Data Index: 670984 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.8271. Min Act: -0.1700

Data Index: 6617529 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.8253. Min Act: -0.1700

Data Index: 1749280 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.7692. Min Act: -0.1700

Data Index: 4709055 (Open Web Text)

Max Activating Token Index: 504

Text #6

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.7254. Min Act: -0.1700

Data Index: 18033 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6796. Min Act: -0.1700

Data Index: 4726715 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.7046. Min Act: -0.1700

Data Index: 1413891 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.7022. Min Act: -0.1700

Data Index: 4127681 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6388. Min Act: -0.1700

Data Index: 6630142 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6522. Min Act: -0.1700

Data Index: 451281 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6573. Min Act: -0.1700

Data Index: 6137985 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6647. Min Act: -0.1700

Data Index: 1344005 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6749. Min Act: -0.1700

Data Index: 8220972 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6756. Min Act: -0.1700

Data Index: 1915207 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6538. Min Act: -0.1700

Data Index: 7807690 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6705. Min Act: -0.1700

Data Index: 7114488 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6444. Min Act: -0.1700

Data Index: 3965641 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 6.1903. Min Range: -6.1903

Max Act: 5.6254. Min Act: -0.1700

Data Index: 1504586 (Open Web Text)

Max Activating Token Index: 6