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

Dataset: Open Web Text

Neuron 963 in Layer 2

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: 4.6763. Min Range: -4.6763

Max Act: 4.6763. Min Act: -0.1700

Data Index: 285303 (Open Web Text)

Max Activating Token Index: 59

Text #1

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6176. Min Act: -0.1700

Data Index: 8503936 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6075. Min Act: -0.1700

Data Index: 4967417 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6032. Min Act: -0.1700

Data Index: 847222 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6079. Min Act: -0.1700

Data Index: 8681301 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6039. Min Act: -0.1700

Data Index: 3589651 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6130. Min Act: -0.1700

Data Index: 4967428 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6121. Min Act: -0.1700

Data Index: 2917794 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.6240. Min Act: -0.1700

Data Index: 2216074 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5739. Min Act: -0.1700

Data Index: 7746525 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5759. Min Act: -0.1700

Data Index: 1629110 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5948. Min Act: -0.1700

Data Index: 7157225 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5795. Min Act: -0.1700

Data Index: 1432171 (Open Web Text)

Max Activating Token Index: 450

Text #13

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5923. Min Act: -0.1700

Data Index: 7035988 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5701. Min Act: -0.1700

Data Index: 6518168 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5790. Min Act: -0.1700

Data Index: 5881923 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5612. Min Act: -0.1700

Data Index: 5439760 (Open Web Text)

Max Activating Token Index: 589

Text #17

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5796. Min Act: -0.1700

Data Index: 5113755 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5917. Min Act: -0.1700

Data Index: 2009552 (Open Web Text)

Max Activating Token Index: 989

Text #19

Max Range: 4.6763. Min Range: -4.6763

Max Act: 4.5732. Min Act: -0.1700

Data Index: 1818442 (Open Web Text)

Max Activating Token Index: 310