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

Dataset: Open Web Text

Neuron 2604 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: 3.6692. Min Range: -3.6692

Max Act: 3.6546. Min Act: -0.1700

Data Index: 4715629 (Open Web Text)

Max Activating Token Index: 953

Text #1

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.6692. Min Act: -0.1700

Data Index: 8528434 (Open Web Text)

Max Activating Token Index: 745

Text #2

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5599. Min Act: -0.1700

Data Index: 5854554 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1266537 (Open Web Text)

Max Activating Token Index: 895

Text #4

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5461. Min Act: -0.1700

Data Index: 3309709 (Open Web Text)

Max Activating Token Index: 132

Text #5

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5179. Min Act: -0.1700

Data Index: 7097532 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4924. Min Act: -0.1700

Data Index: 7499233 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5184. Min Act: -0.1700

Data Index: 2848213 (Open Web Text)

Max Activating Token Index: 942

Text #8

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5221. Min Act: -0.1700

Data Index: 8080920 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4968. Min Act: -0.1700

Data Index: 1581331 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4701. Min Act: -0.1700

Data Index: 3100935 (Open Web Text)

Max Activating Token Index: 970

Text #11

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4994. Min Act: -0.1700

Data Index: 4793111 (Open Web Text)

Max Activating Token Index: 924

Text #12

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4349. Min Act: -0.1700

Data Index: 7355325 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4857. Min Act: -0.1700

Data Index: 6837591 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4685. Min Act: -0.1700

Data Index: 2445040 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4678. Min Act: -0.1700

Data Index: 8069157 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4890. Min Act: -0.1700

Data Index: 4349139 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4643. Min Act: -0.1700

Data Index: 1660284 (Open Web Text)

Max Activating Token Index: 743

Text #18

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4415. Min Act: -0.1700

Data Index: 4204556 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.4276. Min Act: -0.1700

Data Index: 4652186 (Open Web Text)

Max Activating Token Index: 613