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

Dataset: Open Web Text

Neuron 375 in Layer 3

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: 4.5872. Min Range: -4.5872

Max Act: 4.5872. Min Act: -0.1700

Data Index: 1078228 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.5622. Min Act: -0.1700

Data Index: 6361818 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.5080. Min Act: -0.1700

Data Index: 7461032 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.4642. Min Act: -0.1700

Data Index: 3326702 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.4525. Min Act: -0.1700

Data Index: 3397280 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3868. Min Act: -0.1700

Data Index: 4923151 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3348. Min Act: -0.1700

Data Index: 8312110 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3509. Min Act: -0.1700

Data Index: 614337 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3308. Min Act: -0.1700

Data Index: 8189761 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2906. Min Act: -0.1700

Data Index: 8077940 (Open Web Text)

Max Activating Token Index: 867

Text #10

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3543. Min Act: -0.1700

Data Index: 881753 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3219. Min Act: -0.1700

Data Index: 7159908 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2465. Min Act: -0.1700

Data Index: 3838299 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2790. Min Act: -0.1700

Data Index: 4223383 (Open Web Text)

Max Activating Token Index: 422

Text #14

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3206. Min Act: -0.1700

Data Index: 3013285 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2320. Min Act: -0.1700

Data Index: 4706225 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2651. Min Act: -0.1700

Data Index: 1340173 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3052. Min Act: -0.1700

Data Index: 3765455 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.3062. Min Act: -0.1700

Data Index: 7360875 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 4.5872. Min Range: -4.5872

Max Act: 4.2627. Min Act: -0.1700

Data Index: 2977452 (Open Web Text)

Max Activating Token Index: 372