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

Dataset: Open Web Text

Neuron 220 in Layer 5

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: 4.8084. Min Range: -4.8084

Max Act: 4.8084. Min Act: -0.1700

Data Index: 2778028 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.7290. Min Act: -0.1700

Data Index: 4108216 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.7528. Min Act: -0.1700

Data Index: 2473939 (Open Web Text)

Max Activating Token Index: 842

Text #3

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6992. Min Act: -0.1700

Data Index: 8612738 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6686. Min Act: -0.1700

Data Index: 1575819 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6712. Min Act: -0.1700

Data Index: 7154450 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6756. Min Act: -0.1700

Data Index: 4847484 (Open Web Text)

Max Activating Token Index: 155

Text #7

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6292. Min Act: -0.1700

Data Index: 6865653 (Open Web Text)

Max Activating Token Index: 316

Text #8

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6665. Min Act: -0.1700

Data Index: 431800 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6503. Min Act: -0.1700

Data Index: 4108220 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6114. Min Act: -0.1700

Data Index: 675378 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6079. Min Act: -0.1700

Data Index: 4152310 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6083. Min Act: -0.1700

Data Index: 3265329 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6182. Min Act: -0.1700

Data Index: 8461489 (Open Web Text)

Max Activating Token Index: 354

Text #14

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.6387. Min Act: -0.1700

Data Index: 2996011 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.5880. Min Act: -0.1700

Data Index: 1120375 (Open Web Text)

Max Activating Token Index: 800

Text #16

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.5738. Min Act: -0.1700

Data Index: 4417616 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.5894. Min Act: -0.1700

Data Index: 4108213 (Open Web Text)

Max Activating Token Index: 646

Text #18

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.5650. Min Act: -0.1700

Data Index: 550483 (Open Web Text)

Max Activating Token Index: 481

Text #19

Max Range: 4.8084. Min Range: -4.8084

Max Act: 4.5685. Min Act: -0.1700

Data Index: 7431890 (Open Web Text)

Max Activating Token Index: 731