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

Dataset: Open Web Text

Neuron 1223 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: 6.9317. Min Range: -6.9317

Max Act: 6.9317. Min Act: -0.1700

Data Index: 6951983 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.4999. Min Act: -0.1700

Data Index: 1018993 (Open Web Text)

Max Activating Token Index: 770

Text #2

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.5052. Min Act: -0.1700

Data Index: 8802708 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3706. Min Act: -0.1700

Data Index: 3789649 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3949. Min Act: -0.1700

Data Index: 7826131 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2760. Min Act: -0.1700

Data Index: 2705608 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3610. Min Act: -0.1700

Data Index: 6204404 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3302. Min Act: -0.1700

Data Index: 1874914 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3342. Min Act: -0.1700

Data Index: 1635342 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.3227. Min Act: -0.1700

Data Index: 334606 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2986. Min Act: -0.1700

Data Index: 7081075 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2949. Min Act: -0.1700

Data Index: 1697436 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2478. Min Act: -0.1700

Data Index: 4600614 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2470. Min Act: -0.1700

Data Index: 2858953 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2638. Min Act: -0.1700

Data Index: 5893101 (Open Web Text)

Max Activating Token Index: 849

Text #15

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2169. Min Act: -0.1700

Data Index: 2209801 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.2031. Min Act: -0.1700

Data Index: 3690607 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.1841. Min Act: -0.1700

Data Index: 1346268 (Open Web Text)

Max Activating Token Index: 942

Text #18

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.1921. Min Act: -0.1700

Data Index: 4338218 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 6.9317. Min Range: -6.9317

Max Act: 6.1791. Min Act: -0.1700

Data Index: 1745849 (Open Web Text)

Max Activating Token Index: 546