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

Dataset: Open Web Text

Neuron 922 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: 3.3871. Min Range: -3.3871

Max Act: 3.3871. Min Act: -0.1700

Data Index: 5277053 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.3323. Min Act: -0.1700

Data Index: 4807791 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.3222. Min Act: -0.1700

Data Index: 3362765 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.3036. Min Act: -0.1700

Data Index: 8049116 (Open Web Text)

Max Activating Token Index: 411

Text #4

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2966. Min Act: -0.1700

Data Index: 7538926 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2905. Min Act: -0.1700

Data Index: 426829 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2806. Min Act: -0.1700

Data Index: 4456373 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2636. Min Act: -0.1700

Data Index: 5029826 (Open Web Text)

Max Activating Token Index: 841

Text #8

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2379. Min Act: -0.1700

Data Index: 6807501 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2433. Min Act: -0.1700

Data Index: 617279 (Open Web Text)

Max Activating Token Index: 801

Text #10

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2425. Min Act: -0.1700

Data Index: 7314031 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2206. Min Act: -0.1700

Data Index: 8703263 (Open Web Text)

Max Activating Token Index: 969

Text #12

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2236. Min Act: -0.1700

Data Index: 326563 (Open Web Text)

Max Activating Token Index: 235

Text #13

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2099. Min Act: -0.1700

Data Index: 1359591 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2286. Min Act: -0.1700

Data Index: 3118361 (Open Web Text)

Max Activating Token Index: 760

Text #15

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1739. Min Act: -0.1700

Data Index: 1352768 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2121. Min Act: -0.1700

Data Index: 7352874 (Open Web Text)

Max Activating Token Index: 1001

Text #17

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1599. Min Act: -0.1700

Data Index: 4420042 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2033. Min Act: -0.1700

Data Index: 8301232 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.2062. Min Act: -0.1700

Data Index: 5245960 (Open Web Text)

Max Activating Token Index: 167