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

Dataset: Open Web Text

Neuron 1661 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: 3.7825. Min Range: -3.7825

Max Act: 3.7825. Min Act: -0.1700

Data Index: 390117 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7261. Min Act: -0.1700

Data Index: 7570841 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6893. Min Act: -0.1700

Data Index: 2723806 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7015. Min Act: -0.1700

Data Index: 3728341 (Open Web Text)

Max Activating Token Index: 727

Text #4

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6687. Min Act: -0.1700

Data Index: 8051224 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5890. Min Act: -0.1700

Data Index: 3229163 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5734. Min Act: -0.1700

Data Index: 1250961 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5924. Min Act: -0.1700

Data Index: 7738740 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6338. Min Act: -0.1700

Data Index: 2044274 (Open Web Text)

Max Activating Token Index: 709

Text #9

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5968. Min Act: -0.1700

Data Index: 8738976 (Open Web Text)

Max Activating Token Index: 741

Text #10

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5869. Min Act: -0.1700

Data Index: 1392200 (Open Web Text)

Max Activating Token Index: 157

Text #11

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5595. Min Act: -0.1700

Data Index: 3262938 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5678. Min Act: -0.1700

Data Index: 1010904 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5773. Min Act: -0.1700

Data Index: 5102515 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5209. Min Act: -0.1700

Data Index: 31246 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5315. Min Act: -0.1700

Data Index: 3493577 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1421768 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5439. Min Act: -0.1700

Data Index: 3245721 (Open Web Text)

Max Activating Token Index: 837

Text #18

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5316. Min Act: -0.1700

Data Index: 4266929 (Open Web Text)

Max Activating Token Index: 740

Text #19

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5219. Min Act: -0.1700

Data Index: 5144674 (Open Web Text)

Max Activating Token Index: 511