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

Dataset: Open Web Text

Neuron 509 in Layer 1

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: 1.6518. Min Range: -1.6518

Max Act: 1.6518. Min Act: -0.1700

Data Index: 2338066 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6495. Min Act: -0.1700

Data Index: 8514918 (Open Web Text)

Max Activating Token Index: 691

Text #2

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6276. Min Act: -0.1700

Data Index: 8528934 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6190. Min Act: -0.1700

Data Index: 1457724 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6151. Min Act: -0.1700

Data Index: 2473511 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5981. Min Act: -0.1700

Data Index: 6588550 (Open Web Text)

Max Activating Token Index: 961

Text #6

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5984. Min Act: -0.1700

Data Index: 2473510 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6058. Min Act: -0.1700

Data Index: 7650515 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6048. Min Act: -0.1700

Data Index: 4602662 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6033. Min Act: -0.1700

Data Index: 8215877 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6004. Min Act: -0.1700

Data Index: 2636484 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5911. Min Act: -0.1700

Data Index: 3029881 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5939. Min Act: -0.1700

Data Index: 3599036 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.6019. Min Act: -0.1700

Data Index: 8357902 (Open Web Text)

Max Activating Token Index: 801

Text #14

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5958. Min Act: -0.1700

Data Index: 1825096 (Open Web Text)

Max Activating Token Index: 514

Text #15

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5949. Min Act: -0.1700

Data Index: 2330621 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5890. Min Act: -0.1700

Data Index: 3599037 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5991. Min Act: -0.1700

Data Index: 2331677 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5941. Min Act: -0.1700

Data Index: 6585810 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 1.6518. Min Range: -1.6518

Max Act: 1.5883. Min Act: -0.1700

Data Index: 6517228 (Open Web Text)

Max Activating Token Index: 69