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

Dataset: Open Web Text

Neuron 2102 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: 3.5751. Min Range: -3.5751

Max Act: 3.5751. Min Act: -0.1700

Data Index: 5488148 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5207. Min Act: -0.1700

Data Index: 7930361 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5193. Min Act: -0.1700

Data Index: 3285549 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5172. Min Act: -0.1700

Data Index: 32424 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5055. Min Act: -0.1700

Data Index: 864104 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4804. Min Act: -0.1700

Data Index: 1869464 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4771. Min Act: -0.1700

Data Index: 7604760 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5053. Min Act: -0.1700

Data Index: 7539099 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4767. Min Act: -0.1700

Data Index: 7001416 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4913. Min Act: -0.1700

Data Index: 1211323 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5034. Min Act: -0.1700

Data Index: 6181046 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.5035. Min Act: -0.1700

Data Index: 6148541 (Open Web Text)

Max Activating Token Index: 52

Text #12

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4998. Min Act: -0.1700

Data Index: 5799469 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4819. Min Act: -0.1700

Data Index: 5772384 (Open Web Text)

Max Activating Token Index: 56

Text #14

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4822. Min Act: -0.1700

Data Index: 5419064 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4907. Min Act: -0.1700

Data Index: 4673661 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4941. Min Act: -0.1700

Data Index: 4660636 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4804. Min Act: -0.1700

Data Index: 4248203 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4801. Min Act: -0.1700

Data Index: 3299584 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.5751. Min Range: -3.5751

Max Act: 3.4947. Min Act: -0.1700

Data Index: 3265588 (Open Web Text)

Max Activating Token Index: 55