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

Dataset: Open Web Text

Neuron 2864 in Layer 3

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: 3.8506. Min Range: -3.8506

Max Act: 3.8331. Min Act: -0.1700

Data Index: 2730925 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8503. Min Act: -0.1700

Data Index: 1546952 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8406. Min Act: -0.1700

Data Index: 8778616 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8490. Min Act: -0.1700

Data Index: 3688363 (Open Web Text)

Max Activating Token Index: 394

Text #4

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8506. Min Act: -0.1700

Data Index: 6645824 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8249. Min Act: -0.1700

Data Index: 6003695 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7775. Min Act: -0.1700

Data Index: 4731876 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7947. Min Act: -0.1700

Data Index: 827569 (Open Web Text)

Max Activating Token Index: 274

Text #8

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8154. Min Act: -0.1700

Data Index: 8144936 (Open Web Text)

Max Activating Token Index: 497

Text #9

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7855. Min Act: -0.1700

Data Index: 7222627 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8041. Min Act: -0.1700

Data Index: 3843847 (Open Web Text)

Max Activating Token Index: 390

Text #11

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7875. Min Act: -0.1700

Data Index: 6754898 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7399. Min Act: -0.1700

Data Index: 3030156 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7575. Min Act: -0.1700

Data Index: 2241778 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7347. Min Act: -0.1700

Data Index: 1579805 (Open Web Text)

Max Activating Token Index: 185

Text #15

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7236. Min Act: -0.1700

Data Index: 7891669 (Open Web Text)

Max Activating Token Index: 510

Text #16

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7451. Min Act: -0.1700

Data Index: 444445 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7580. Min Act: -0.1700

Data Index: 7419911 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7573. Min Act: -0.1700

Data Index: 815874 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6857. Min Act: -0.1700

Data Index: 8097582 (Open Web Text)

Max Activating Token Index: 201