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

Dataset: Open Web Text

Neuron 929 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: 4.7322. Min Range: -4.7322

Max Act: 4.7322. Min Act: -0.1700

Data Index: 2149022 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.6932. Min Act: -0.1700

Data Index: 2149024 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5574. Min Act: -0.1700

Data Index: 4369324 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5326. Min Act: -0.1700

Data Index: 4516693 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5387. Min Act: -0.1700

Data Index: 2593023 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4841. Min Act: -0.1700

Data Index: 380263 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5060. Min Act: -0.1700

Data Index: 2188511 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5156. Min Act: -0.1700

Data Index: 7936978 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4734. Min Act: -0.1700

Data Index: 655269 (Open Web Text)

Max Activating Token Index: 611

Text #9

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4747. Min Act: -0.1700

Data Index: 1512602 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4907. Min Act: -0.1700

Data Index: 7363468 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4651. Min Act: -0.1700

Data Index: 4045653 (Open Web Text)

Max Activating Token Index: 143

Text #12

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.5028. Min Act: -0.1700

Data Index: 1512601 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4919. Min Act: -0.1700

Data Index: 3646726 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4720. Min Act: -0.1700

Data Index: 2149021 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4819. Min Act: -0.1700

Data Index: 6982031 (Open Web Text)

Max Activating Token Index: 124

Text #16

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4688. Min Act: -0.1700

Data Index: 510670 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4764. Min Act: -0.1700

Data Index: 3141715 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4775. Min Act: -0.1700

Data Index: 5749839 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 4.7322. Min Range: -4.7322

Max Act: 4.4178. Min Act: -0.1700

Data Index: 4366487 (Open Web Text)

Max Activating Token Index: 494