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

Dataset: Open Web Text

Neuron 1040 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: 2.9606. Min Range: -2.9606

Max Act: 2.9606. Min Act: -0.1700

Data Index: 1214107 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9086. Min Act: -0.1700

Data Index: 4746777 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9210. Min Act: -0.1700

Data Index: 4985769 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9210. Min Act: -0.1699

Data Index: 3659463 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9210. Min Act: -0.1700

Data Index: 1535281 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9036. Min Act: -0.1700

Data Index: 4377867 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.9155. Min Act: -0.1700

Data Index: 7007117 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8935. Min Act: -0.1700

Data Index: 5828235 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8963. Min Act: -0.1700

Data Index: 4965785 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8725. Min Act: -0.1700

Data Index: 1766989 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8638. Min Act: -0.1700

Data Index: 6729601 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8603. Min Act: -0.1700

Data Index: 7316559 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8651. Min Act: -0.1700

Data Index: 4128257 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8561. Min Act: -0.1700

Data Index: 4884683 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8651. Min Act: -0.1700

Data Index: 5304979 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8544. Min Act: -0.1700

Data Index: 6263360 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8450. Min Act: -0.1700

Data Index: 6420543 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8416. Min Act: -0.1700

Data Index: 5313643 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8261. Min Act: -0.1700

Data Index: 5955195 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9606. Min Range: -2.9606

Max Act: 2.8276. Min Act: -0.1700

Data Index: 5646689 (Open Web Text)

Max Activating Token Index: 3