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

Dataset: Open Web Text

Neuron 2347 in Layer 4

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: 4.4947. Min Range: -4.4947

Max Act: 4.4947. Min Act: -0.1700

Data Index: 6747374 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.4270. Min Act: -0.1700

Data Index: 730310 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.3502. Min Act: -0.1700

Data Index: 2962393 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2436. Min Act: -0.1700

Data Index: 5658926 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2356. Min Act: -0.1700

Data Index: 8044139 (Open Web Text)

Max Activating Token Index: 890

Text #5

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2230. Min Act: -0.1700

Data Index: 2693392 (Open Web Text)

Max Activating Token Index: 957

Text #6

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.1960. Min Act: -0.1700

Data Index: 4191182 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.1637. Min Act: -0.1700

Data Index: 7696905 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.1642. Min Act: -0.1700

Data Index: 1532568 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.1134. Min Act: -0.1700

Data Index: 2409731 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0715. Min Act: -0.1700

Data Index: 6768300 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0648. Min Act: -0.1700

Data Index: 3121762 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0485. Min Act: -0.1700

Data Index: 3645891 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0421. Min Act: -0.1700

Data Index: 3643734 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0521. Min Act: -0.1700

Data Index: 4961478 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9822. Min Act: -0.1700

Data Index: 2171704 (Open Web Text)

Max Activating Token Index: 188

Text #16

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0040. Min Act: -0.1700

Data Index: 2701656 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9874. Min Act: -0.1700

Data Index: 2455997 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9768. Min Act: -0.1700

Data Index: 7662763 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9519. Min Act: -0.1700

Data Index: 4521144 (Open Web Text)

Max Activating Token Index: 345