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

Dataset: Open Web Text

Neuron 1679 in Layer 6

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: 4.2504. Min Range: -4.2504

Max Act: 4.2504. Min Act: -0.1700

Data Index: 3278175 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 4.2504. Min Range: -4.2504

Max Act: 4.0806. Min Act: -0.1700

Data Index: 5115295 (Open Web Text)

Max Activating Token Index: 957

Text #2

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.9574. Min Act: -0.1700

Data Index: 1127147 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.7803. Min Act: -0.1700

Data Index: 7677037 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.8362. Min Act: -0.1700

Data Index: 7812667 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.7867. Min Act: -0.1700

Data Index: 4785911 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.6662. Min Act: -0.1700

Data Index: 6334574 (Open Web Text)

Max Activating Token Index: 681

Text #7

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.5349. Min Act: -0.1700

Data Index: 8667458 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.5318. Min Act: -0.1700

Data Index: 5651533 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.4624. Min Act: -0.1700

Data Index: 3164705 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3920. Min Act: -0.1700

Data Index: 6113460 (Open Web Text)

Max Activating Token Index: 840

Text #11

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3881. Min Act: -0.1700

Data Index: 2968613 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3779. Min Act: -0.1700

Data Index: 2569664 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3542. Min Act: -0.1700

Data Index: 1649902 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3595. Min Act: -0.1700

Data Index: 5804918 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3425. Min Act: -0.1700

Data Index: 3517144 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.3063. Min Act: -0.1700

Data Index: 4731172 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.2801. Min Act: -0.1700

Data Index: 417999 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.2476. Min Act: -0.1700

Data Index: 5075911 (Open Web Text)

Max Activating Token Index: 858

Text #19

Max Range: 4.2504. Min Range: -4.2504

Max Act: 3.2687. Min Act: -0.1700

Data Index: 8582245 (Open Web Text)

Max Activating Token Index: 839