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

Dataset: Open Web Text

Neuron 1736 in Layer 2

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: 4.3801. Min Range: -4.3801

Max Act: 4.3801. Min Act: -0.1700

Data Index: 4620340 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2358. Min Act: -0.1700

Data Index: 6554621 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2592. Min Act: -0.1700

Data Index: 8370327 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2554. Min Act: -0.1700

Data Index: 3143967 (Open Web Text)

Max Activating Token Index: 908

Text #4

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2509. Min Act: -0.1700

Data Index: 8370326 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2583. Min Act: -0.1700

Data Index: 1832069 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2181. Min Act: -0.1700

Data Index: 7903095 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2190. Min Act: -0.1700

Data Index: 7195614 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2143. Min Act: -0.1700

Data Index: 6532774 (Open Web Text)

Max Activating Token Index: 906

Text #9

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2232. Min Act: -0.1700

Data Index: 6532775 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2153. Min Act: -0.1700

Data Index: 4818557 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2237. Min Act: -0.1700

Data Index: 4376096 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2183. Min Act: -0.1700

Data Index: 7985647 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2304. Min Act: -0.1700

Data Index: 7809118 (Open Web Text)

Max Activating Token Index: 454

Text #14

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2017. Min Act: -0.1700

Data Index: 770159 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1772. Min Act: -0.1700

Data Index: 4706158 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1837. Min Act: -0.1700

Data Index: 5885955 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2122. Min Act: -0.1700

Data Index: 4624275 (Open Web Text)

Max Activating Token Index: 692

Text #18

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1785. Min Act: -0.1700

Data Index: 4245286 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1948. Min Act: -0.1700

Data Index: 6566953 (Open Web Text)

Max Activating Token Index: 4