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

Dataset: Open Web Text

Neuron 2923 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: 4.7818. Min Range: -4.7818

Max Act: 4.7818. Min Act: -0.1700

Data Index: 2604022 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.7516. Min Act: -0.1700

Data Index: 8662297 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6915. Min Act: -0.1700

Data Index: 3949782 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6426. Min Act: -0.1700

Data Index: 2513441 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.6192. Min Act: -0.1700

Data Index: 4687894 (Open Web Text)

Max Activating Token Index: 325

Text #5

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5897. Min Act: -0.1700

Data Index: 3568747 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5725. Min Act: -0.1700

Data Index: 4784009 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5752. Min Act: -0.1700

Data Index: 2995275 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5462. Min Act: -0.1700

Data Index: 7221032 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5207. Min Act: -0.1700

Data Index: 7273925 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5311. Min Act: -0.1700

Data Index: 2301910 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5395. Min Act: -0.1700

Data Index: 5765560 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4936. Min Act: -0.1700

Data Index: 1332677 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4945. Min Act: -0.1700

Data Index: 3509091 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5045. Min Act: -0.1700

Data Index: 7898905 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.5009. Min Act: -0.1700

Data Index: 2593077 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4823. Min Act: -0.1700

Data Index: 6968833 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4594. Min Act: -0.1700

Data Index: 234564 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4656. Min Act: -0.1700

Data Index: 5283790 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 4.7818. Min Range: -4.7818

Max Act: 4.4742. Min Act: -0.1700

Data Index: 7799027 (Open Web Text)

Max Activating Token Index: 511