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

Dataset: Open Web Text

Neuron 2383 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: 4.8343. Min Range: -4.8343

Max Act: 4.8343. Min Act: -0.1700

Data Index: 5367266 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.8017. Min Act: -0.1700

Data Index: 8808798 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7656. Min Act: -0.1700

Data Index: 4044411 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7935. Min Act: -0.1700

Data Index: 8327115 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7563. Min Act: -0.1700

Data Index: 3912356 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7678. Min Act: -0.1700

Data Index: 2374233 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7444. Min Act: -0.1700

Data Index: 2514593 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7138. Min Act: -0.1700

Data Index: 1186138 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7317. Min Act: -0.1700

Data Index: 4431844 (Open Web Text)

Max Activating Token Index: 373

Text #9

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.7150. Min Act: -0.1700

Data Index: 3985589 (Open Web Text)

Max Activating Token Index: 427

Text #10

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6673. Min Act: -0.1700

Data Index: 5593419 (Open Web Text)

Max Activating Token Index: 857

Text #11

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6315. Min Act: -0.1700

Data Index: 5708254 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6385. Min Act: -0.1700

Data Index: 4202608 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6550. Min Act: -0.1700

Data Index: 6586008 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6480. Min Act: -0.1700

Data Index: 7648557 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6408. Min Act: -0.1700

Data Index: 4328721 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6349. Min Act: -0.1700

Data Index: 5605081 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6512. Min Act: -0.1700

Data Index: 45199 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6740. Min Act: -0.1700

Data Index: 4250577 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 4.8343. Min Range: -4.8343

Max Act: 4.6159. Min Act: -0.1700

Data Index: 2769410 (Open Web Text)

Max Activating Token Index: 58