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

Dataset: Open Web Text

Neuron 217 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: 3.2028. Min Range: -3.2028

Max Act: 3.2028. Min Act: -0.1700

Data Index: 368160 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1555. Min Act: -0.1700

Data Index: 5102428 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1176. Min Act: -0.1700

Data Index: 3826815 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1134. Min Act: -0.1700

Data Index: 3536019 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0984. Min Act: -0.1700

Data Index: 3071390 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1116. Min Act: -0.1700

Data Index: 5157898 (Open Web Text)

Max Activating Token Index: 491

Text #6

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1030. Min Act: -0.1700

Data Index: 6653911 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.1000. Min Act: -0.1700

Data Index: 4057705 (Open Web Text)

Max Activating Token Index: 542

Text #8

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0945. Min Act: -0.1700

Data Index: 2593308 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0763. Min Act: -0.1700

Data Index: 416971 (Open Web Text)

Max Activating Token Index: 139

Text #10

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0885. Min Act: -0.1700

Data Index: 2654513 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0781. Min Act: -0.1700

Data Index: 8107818 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0799. Min Act: -0.1700

Data Index: 873820 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0689. Min Act: -0.1700

Data Index: 6878891 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0632. Min Act: -0.1700

Data Index: 8403891 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0671. Min Act: -0.1700

Data Index: 8189841 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0516. Min Act: -0.1700

Data Index: 2220446 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0582. Min Act: -0.1700

Data Index: 6542283 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0514. Min Act: -0.1700

Data Index: 4685878 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 3.2028. Min Range: -3.2028

Max Act: 3.0422. Min Act: -0.1700

Data Index: 6556904 (Open Web Text)

Max Activating Token Index: 351