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

Dataset: Open Web Text

Neuron 2562 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: 1.3621. Min Range: -1.3621

Max Act: 1.3621. Min Act: -0.1700

Data Index: 169392 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3358. Min Act: -0.1700

Data Index: 4506365 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3349. Min Act: -0.1700

Data Index: 4009848 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3194. Min Act: -0.1700

Data Index: 3280616 (Open Web Text)

Max Activating Token Index: 267

Text #4

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3220. Min Act: -0.1700

Data Index: 4323876 (Open Web Text)

Max Activating Token Index: 133

Text #5

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3258. Min Act: -0.1700

Data Index: 7080637 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3130. Min Act: -0.1700

Data Index: 3015448 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2945. Min Act: -0.1700

Data Index: 2395316 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3045. Min Act: -0.1700

Data Index: 5489291 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2939. Min Act: -0.1693

Data Index: 169393 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2986. Min Act: -0.1700

Data Index: 3791293 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2885. Min Act: -0.1700

Data Index: 6650330 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3053. Min Act: -0.1700

Data Index: 8708389 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2769. Min Act: -0.1700

Data Index: 279096 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2773. Min Act: -0.1700

Data Index: 3516498 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2703. Min Act: -0.1700

Data Index: 853949 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2801. Min Act: -0.1700

Data Index: 5884950 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2761. Min Act: -0.1695

Data Index: 7658001 (Open Web Text)

Max Activating Token Index: 869

Text #18

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2717. Min Act: -0.1696

Data Index: 8799136 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2793. Min Act: -0.1700

Data Index: 4944957 (Open Web Text)

Max Activating Token Index: 889