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

Dataset: Open Web Text

Neuron 1815 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: 4.0425. Min Range: -4.0425

Max Act: 4.0425. Min Act: -0.1700

Data Index: 8150849 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0171. Min Act: -0.1700

Data Index: 4521837 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0168. Min Act: -0.1700

Data Index: 7109543 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0237. Min Act: -0.1700

Data Index: 3201006 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0012. Min Act: -0.1700

Data Index: 244876 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0071. Min Act: -0.1700

Data Index: 3120612 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0038. Min Act: -0.1700

Data Index: 5591804 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0215. Min Act: -0.1700

Data Index: 244871 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9857. Min Act: -0.1700

Data Index: 226956 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0034. Min Act: -0.1700

Data Index: 6713745 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0027. Min Act: -0.1700

Data Index: 8514127 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9881. Min Act: -0.1700

Data Index: 226945 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 4.0425. Min Range: -4.0425

Max Act: 4.0087. Min Act: -0.1700

Data Index: 4499868 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9470. Min Act: -0.1700

Data Index: 226961 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9542. Min Act: -0.1700

Data Index: 8180167 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9727. Min Act: -0.1700

Data Index: 11013 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9769. Min Act: -0.1700

Data Index: 3447303 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9345. Min Act: -0.1700

Data Index: 7765963 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9688. Min Act: -0.1700

Data Index: 4262462 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.0425. Min Range: -4.0425

Max Act: 3.9023. Min Act: -0.1700

Data Index: 6026654 (Open Web Text)

Max Activating Token Index: 534