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

Dataset: Open Web Text

Neuron 1383 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: 3.5357. Min Range: -3.5357

Max Act: 3.5357. Min Act: -0.1700

Data Index: 2835318 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.5210. Min Act: -0.1700

Data Index: 2154034 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.5100. Min Act: -0.1700

Data Index: 5510656 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.5169. Min Act: -0.1700

Data Index: 7479016 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4879. Min Act: -0.1700

Data Index: 7547194 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4811. Min Act: -0.1700

Data Index: 5622474 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4817. Min Act: -0.1700

Data Index: 7370653 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4858. Min Act: -0.1700

Data Index: 7001275 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4717. Min Act: -0.1700

Data Index: 6800554 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4858. Min Act: -0.1700

Data Index: 6222841 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4587. Min Act: -0.1700

Data Index: 4393919 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4645. Min Act: -0.1700

Data Index: 4112700 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4651. Min Act: -0.1700

Data Index: 4842780 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4637. Min Act: -0.1700

Data Index: 3975286 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4633. Min Act: -0.1700

Data Index: 6050741 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1300602 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4716. Min Act: -0.1700

Data Index: 3929881 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4633. Min Act: -0.1700

Data Index: 5061632 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4593. Min Act: -0.1700

Data Index: 3199326 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.5357. Min Range: -3.5357

Max Act: 3.4648. Min Act: -0.1700

Data Index: 3880645 (Open Web Text)

Max Activating Token Index: 3