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

Dataset: Open Web Text

Neuron 2653 in Layer 3

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: 4.5522. Min Range: -4.5522

Max Act: 4.5522. Min Act: -0.1700

Data Index: 7597744 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.4115. Min Act: -0.1700

Data Index: 2977510 (Open Web Text)

Max Activating Token Index: 512

Text #2

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.3575. Min Act: -0.1700

Data Index: 6305544 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.3275. Min Act: -0.1700

Data Index: 6173427 (Open Web Text)

Max Activating Token Index: 199

Text #4

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2958. Min Act: -0.1700

Data Index: 2077903 (Open Web Text)

Max Activating Token Index: 349

Text #5

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.3177. Min Act: -0.1700

Data Index: 214958 (Open Web Text)

Max Activating Token Index: 852

Text #6

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2913. Min Act: -0.1700

Data Index: 5175565 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.3075. Min Act: -0.1700

Data Index: 4576453 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.3049. Min Act: -0.1700

Data Index: 1380272 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2766. Min Act: -0.1700

Data Index: 1632891 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2555. Min Act: -0.1700

Data Index: 1943791 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2891. Min Act: -0.1700

Data Index: 8108182 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2674. Min Act: -0.1700

Data Index: 7161945 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2883. Min Act: -0.1700

Data Index: 1237199 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2586. Min Act: -0.1700

Data Index: 4154118 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2213. Min Act: -0.1700

Data Index: 244029 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2564. Min Act: -0.1700

Data Index: 3401537 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2071. Min Act: -0.1700

Data Index: 6577839 (Open Web Text)

Max Activating Token Index: 872

Text #18

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2317. Min Act: -0.1700

Data Index: 2606157 (Open Web Text)

Max Activating Token Index: 388

Text #19

Max Range: 4.5522. Min Range: -4.5522

Max Act: 4.2145. Min Act: -0.1700

Data Index: 5200873 (Open Web Text)

Max Activating Token Index: 998