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

Dataset: Open Web Text

Neuron 2955 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: 5.4281. Min Range: -5.4281

Max Act: 5.4281. Min Act: -0.1700

Data Index: 2343311 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.3966. Min Act: -0.1700

Data Index: 2691256 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.3529. Min Act: -0.1700

Data Index: 6324818 (Open Web Text)

Max Activating Token Index: 64

Text #3

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.3726. Min Act: -0.1700

Data Index: 6412871 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.3564. Min Act: -0.1700

Data Index: 4024868 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2889. Min Act: -0.1700

Data Index: 3797469 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2963. Min Act: -0.1700

Data Index: 7007357 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2827. Min Act: -0.1700

Data Index: 6491875 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2516. Min Act: -0.1700

Data Index: 3257553 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2495. Min Act: -0.1700

Data Index: 5213958 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2554. Min Act: -0.1700

Data Index: 3112045 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2323. Min Act: -0.1700

Data Index: 407118 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1981. Min Act: -0.1700

Data Index: 4941442 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1953. Min Act: -0.1700

Data Index: 1876986 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2103. Min Act: -0.1700

Data Index: 2910193 (Open Web Text)

Max Activating Token Index: 782

Text #15

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.2176. Min Act: -0.1700

Data Index: 7748038 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1711. Min Act: -0.1700

Data Index: 4906184 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1747. Min Act: -0.1700

Data Index: 772563 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1948. Min Act: -0.1700

Data Index: 731553 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 5.4281. Min Range: -5.4281

Max Act: 5.1692. Min Act: -0.1700

Data Index: 3449650 (Open Web Text)

Max Activating Token Index: 503