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

Dataset: Open Web Text

Neuron 1061 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: 5.2085. Min Range: -5.2085

Max Act: 5.2085. Min Act: -0.1700

Data Index: 4496315 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.9465. Min Act: -0.1700

Data Index: 4650325 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.8907. Min Act: -0.1700

Data Index: 1699363 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.8399. Min Act: -0.1700

Data Index: 2590036 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.8616. Min Act: -0.1700

Data Index: 7129072 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.8086. Min Act: -0.1700

Data Index: 5195634 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7625. Min Act: -0.1700

Data Index: 3051862 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7749. Min Act: -0.1700

Data Index: 2406574 (Open Web Text)

Max Activating Token Index: 807

Text #8

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7344. Min Act: -0.1700

Data Index: 4857249 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7344. Min Act: -0.1700

Data Index: 3665611 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7509. Min Act: -0.1700

Data Index: 1670684 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7276. Min Act: -0.1700

Data Index: 2753754 (Open Web Text)

Max Activating Token Index: 298

Text #12

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7142. Min Act: -0.1700

Data Index: 1603054 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7509. Min Act: -0.1700

Data Index: 713669 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7474. Min Act: -0.1700

Data Index: 800008 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7605. Min Act: -0.1700

Data Index: 4337073 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7411. Min Act: -0.1700

Data Index: 1299951 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.6948. Min Act: -0.1700

Data Index: 2291970 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7137. Min Act: -0.1700

Data Index: 5376469 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.2085. Min Range: -5.2085

Max Act: 4.7100. Min Act: -0.1700

Data Index: 5687917 (Open Web Text)

Max Activating Token Index: 1014