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

Dataset: Open Web Text

Neuron 524 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: 4.4490. Min Range: -4.4490

Max Act: 4.4490. Min Act: -0.1700

Data Index: 310484 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.3151. Min Act: -0.1700

Data Index: 310462 (Open Web Text)

Max Activating Token Index: 778

Text #2

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.2362. Min Act: -0.1700

Data Index: 310483 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.2949. Min Act: -0.1700

Data Index: 310461 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.2174. Min Act: -0.1700

Data Index: 310469 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.1673. Min Act: -0.1700

Data Index: 1788917 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.1909. Min Act: -0.1700

Data Index: 8266587 (Open Web Text)

Max Activating Token Index: 816

Text #7

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.1369. Min Act: -0.1700

Data Index: 935311 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.1223. Min Act: -0.1700

Data Index: 310470 (Open Web Text)

Max Activating Token Index: 935

Text #9

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.0504. Min Act: -0.1700

Data Index: 214269 (Open Web Text)

Max Activating Token Index: 723

Text #10

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.0563. Min Act: -0.1700

Data Index: 6270654 (Open Web Text)

Max Activating Token Index: 799

Text #11

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.0637. Min Act: -0.1700

Data Index: 6098762 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9987. Min Act: -0.1700

Data Index: 4431642 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.0105. Min Act: -0.1700

Data Index: 5221282 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 4.4490. Min Range: -4.4490

Max Act: 4.0033. Min Act: -0.1700

Data Index: 7741625 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9742. Min Act: -0.1700

Data Index: 959939 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9478. Min Act: -0.1700

Data Index: 4431641 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9318. Min Act: -0.1700

Data Index: 6047432 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9261. Min Act: -0.1700

Data Index: 4373992 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 4.4490. Min Range: -4.4490

Max Act: 3.9311. Min Act: -0.1700

Data Index: 310488 (Open Web Text)

Max Activating Token Index: 587