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

Dataset: Open Web Text

Neuron 821 in Layer 4

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: 3.4777. Min Range: -3.4777

Max Act: 3.4777. Min Act: -0.1700

Data Index: 2381313 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.4445. Min Act: -0.1700

Data Index: 6211433 (Open Web Text)

Max Activating Token Index: 908

Text #2

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.3934. Min Act: -0.1700

Data Index: 415757 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.3651. Min Act: -0.1700

Data Index: 7724605 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.3612. Min Act: -0.1700

Data Index: 3013325 (Open Web Text)

Max Activating Token Index: 974

Text #5

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.3109. Min Act: -0.1700

Data Index: 8312916 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2916. Min Act: -0.1700

Data Index: 6996637 (Open Web Text)

Max Activating Token Index: 650

Text #7

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2944. Min Act: -0.1700

Data Index: 1571740 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2862. Min Act: -0.1700

Data Index: 2939857 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2815. Min Act: -0.1700

Data Index: 4020116 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2680. Min Act: -0.1700

Data Index: 7900091 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2898. Min Act: -0.1700

Data Index: 8143546 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2913. Min Act: -0.1700

Data Index: 2537523 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2526. Min Act: -0.1700

Data Index: 383508 (Open Web Text)

Max Activating Token Index: 583

Text #14

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2884. Min Act: -0.1700

Data Index: 2233709 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2323. Min Act: -0.1700

Data Index: 6067392 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2528. Min Act: -0.1700

Data Index: 7235334 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1189544 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2284. Min Act: -0.1700

Data Index: 768678 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 3.4777. Min Range: -3.4777

Max Act: 3.2261. Min Act: -0.1700

Data Index: 2992784 (Open Web Text)

Max Activating Token Index: 794