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

Dataset: Open Web Text

Neuron 991 in Layer 5

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: 3.0430. Min Range: -3.0430

Max Act: 3.0430. Min Act: -0.1700

Data Index: 1629964 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 3.0430. Min Range: -3.0430

Max Act: 3.0426. Min Act: -0.1700

Data Index: 8006973 (Open Web Text)

Max Activating Token Index: 772

Text #2

Max Range: 3.0430. Min Range: -3.0430

Max Act: 3.0126. Min Act: -0.1700

Data Index: 8295441 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9865. Min Act: -0.1700

Data Index: 2119134 (Open Web Text)

Max Activating Token Index: 1016

Text #4

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9994. Min Act: -0.1700

Data Index: 5862486 (Open Web Text)

Max Activating Token Index: 794

Text #5

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9827. Min Act: -0.1700

Data Index: 383088 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9906. Min Act: -0.1700

Data Index: 2758857 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9756. Min Act: -0.1700

Data Index: 7220909 (Open Web Text)

Max Activating Token Index: 243

Text #8

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9871. Min Act: -0.1700

Data Index: 8278368 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9942. Min Act: -0.1700

Data Index: 8623497 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9676. Min Act: -0.1700

Data Index: 3811316 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9198. Min Act: -0.1700

Data Index: 3370304 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9220. Min Act: -0.1700

Data Index: 6586493 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9168. Min Act: -0.1700

Data Index: 7896037 (Open Web Text)

Max Activating Token Index: 140

Text #14

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9467. Min Act: -0.1700

Data Index: 1398667 (Open Web Text)

Max Activating Token Index: 549

Text #15

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9189. Min Act: -0.1700

Data Index: 5817967 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9307. Min Act: -0.1700

Data Index: 7873687 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9374. Min Act: -0.1700

Data Index: 5422318 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9364. Min Act: -0.1700

Data Index: 6867714 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 3.0430. Min Range: -3.0430

Max Act: 2.9283. Min Act: -0.1700

Data Index: 6860711 (Open Web Text)

Max Activating Token Index: 728