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

Dataset: Open Web Text

Neuron 992 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: 3.3665. Min Range: -3.3665

Max Act: 3.3665. Min Act: -0.1700

Data Index: 3631086 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3470. Min Act: -0.1700

Data Index: 548788 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3185. Min Act: -0.1700

Data Index: 2754852 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.3038. Min Act: -0.1700

Data Index: 7404465 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2843. Min Act: -0.1700

Data Index: 4755600 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2874. Min Act: -0.1700

Data Index: 3934815 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2773. Min Act: -0.1700

Data Index: 130762 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2688. Min Act: -0.1700

Data Index: 1131637 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2618. Min Act: -0.1700

Data Index: 702309 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2745. Min Act: -0.1700

Data Index: 7686891 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2584. Min Act: -0.1700

Data Index: 757943 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2534. Min Act: -0.1700

Data Index: 564946 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2516. Min Act: -0.1700

Data Index: 4620080 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2505. Min Act: -0.1700

Data Index: 3077246 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2536. Min Act: -0.1700

Data Index: 3040089 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2467. Min Act: -0.1700

Data Index: 6948993 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2460. Min Act: -0.1700

Data Index: 5784172 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2616. Min Act: -0.1700

Data Index: 5784171 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2580. Min Act: -0.1700

Data Index: 1237974 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3665. Min Range: -3.3665

Max Act: 3.2442. Min Act: -0.1700

Data Index: 4568468 (Open Web Text)

Max Activating Token Index: 3