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

Dataset: Open Web Text

Neuron 133 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: 1.8002. Min Range: -1.8002

Max Act: 1.8002. Min Act: -0.1700

Data Index: 6585018 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7860. Min Act: -0.1700

Data Index: 1308430 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7464. Min Act: -0.1700

Data Index: 2788754 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7332. Min Act: -0.1700

Data Index: 6453801 (Open Web Text)

Max Activating Token Index: 738

Text #4

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7318. Min Act: -0.1700

Data Index: 5118921 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7330. Min Act: -0.1700

Data Index: 8203073 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7317. Min Act: -0.1700

Data Index: 6605109 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7181. Min Act: -0.1700

Data Index: 1546030 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7125. Min Act: -0.1699

Data Index: 5128600 (Open Web Text)

Max Activating Token Index: 241

Text #9

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6984. Min Act: -0.1700

Data Index: 2798357 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7085. Min Act: -0.1700

Data Index: 6453800 (Open Web Text)

Max Activating Token Index: 928

Text #11

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6966. Min Act: -0.1700

Data Index: 2284795 (Open Web Text)

Max Activating Token Index: 935

Text #12

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6902. Min Act: -0.1700

Data Index: 872630 (Open Web Text)

Max Activating Token Index: 793

Text #13

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6954. Min Act: -0.1700

Data Index: 904876 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6737. Min Act: -0.1700

Data Index: 1862588 (Open Web Text)

Max Activating Token Index: 842

Text #15

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6883. Min Act: -0.1700

Data Index: 5461992 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6899. Min Act: -0.1700

Data Index: 4294498 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6838. Min Act: -0.1700

Data Index: 585770 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6894. Min Act: -0.1700

Data Index: 834128 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6778. Min Act: -0.1700

Data Index: 3440365 (Open Web Text)

Max Activating Token Index: 346