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

Dataset: Open Web Text

Neuron 2096 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: 3.4130. Min Range: -3.4130

Max Act: 3.4130. Min Act: -0.1700

Data Index: 6243854 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.4042. Min Act: -0.1700

Data Index: 2205180 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3966. Min Act: -0.1700

Data Index: 4489284 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3949. Min Act: -0.1700

Data Index: 3552123 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.4104. Min Act: -0.1700

Data Index: 7072061 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3703. Min Act: -0.1700

Data Index: 2189648 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3754. Min Act: -0.1700

Data Index: 8279436 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3648. Min Act: -0.1700

Data Index: 8028033 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3793. Min Act: -0.1700

Data Index: 3129377 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3762. Min Act: -0.1700

Data Index: 6684852 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3920. Min Act: -0.1700

Data Index: 6532171 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3688. Min Act: -0.1700

Data Index: 2467448 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3466. Min Act: -0.1700

Data Index: 57544 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3346. Min Act: -0.1700

Data Index: 5109942 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3400. Min Act: -0.1700

Data Index: 619119 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3350. Min Act: -0.1700

Data Index: 5311012 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3573. Min Act: -0.1700

Data Index: 5582410 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3412. Min Act: -0.1700

Data Index: 6128044 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3602. Min Act: -0.1700

Data Index: 872284 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 3.4130. Min Range: -3.4130

Max Act: 3.3388. Min Act: -0.1700

Data Index: 6225935 (Open Web Text)

Max Activating Token Index: 6