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

Dataset: Open Web Text

Neuron 2321 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: 4.7648. Min Range: -4.7648

Max Act: 4.7648. Min Act: -0.1700

Data Index: 3891344 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.6568. Min Act: -0.1700

Data Index: 607514 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5345. Min Act: -0.1700

Data Index: 4097206 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5312. Min Act: -0.1700

Data Index: 5731557 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.5185. Min Act: -0.1700

Data Index: 1068253 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4730. Min Act: -0.1700

Data Index: 6067952 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4488. Min Act: -0.1700

Data Index: 1168515 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4179. Min Act: -0.1700

Data Index: 803170 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4394. Min Act: -0.1700

Data Index: 2161543 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3520. Min Act: -0.1700

Data Index: 8469122 (Open Web Text)

Max Activating Token Index: 808

Text #10

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.4056. Min Act: -0.1700

Data Index: 2911417 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3614. Min Act: -0.1700

Data Index: 4080928 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3362. Min Act: -0.1700

Data Index: 7808724 (Open Web Text)

Max Activating Token Index: 880

Text #13

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3657. Min Act: -0.1700

Data Index: 7608815 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3427. Min Act: -0.1700

Data Index: 946913 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3762. Min Act: -0.1700

Data Index: 4688994 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3572. Min Act: -0.1700

Data Index: 7897999 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3910. Min Act: -0.1700

Data Index: 310552 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.3663. Min Act: -0.1700

Data Index: 1883236 (Open Web Text)

Max Activating Token Index: 622

Text #19

Max Range: 4.7648. Min Range: -4.7648

Max Act: 4.2951. Min Act: -0.1700

Data Index: 8513956 (Open Web Text)

Max Activating Token Index: 1003