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

Dataset: Open Web Text

Neuron 1979 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: 1.9396. Min Range: -1.9396

Max Act: 1.9396. Min Act: -0.1700

Data Index: 2891067 (Open Web Text)

Max Activating Token Index: 551

Text #1

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8605. Min Act: -0.1700

Data Index: 921484 (Open Web Text)

Max Activating Token Index: 381

Text #2

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8543. Min Act: -0.1700

Data Index: 7964406 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8329. Min Act: -0.1700

Data Index: 7279596 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8288. Min Act: -0.1700

Data Index: 2506165 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8347. Min Act: -0.1700

Data Index: 4506558 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8416. Min Act: -0.1700

Data Index: 7536517 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8251. Min Act: -0.1700

Data Index: 7249298 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8347. Min Act: -0.1700

Data Index: 8665221 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8176. Min Act: -0.1700

Data Index: 4777809 (Open Web Text)

Max Activating Token Index: 888

Text #10

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8295. Min Act: -0.1700

Data Index: 7013390 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8178. Min Act: -0.1700

Data Index: 629648 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7943. Min Act: -0.1700

Data Index: 4030540 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7948. Min Act: -0.1700

Data Index: 6381098 (Open Web Text)

Max Activating Token Index: 85

Text #14

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8042. Min Act: -0.1700

Data Index: 2564438 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7952. Min Act: -0.1700

Data Index: 36878 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7882. Min Act: -0.1700

Data Index: 4274024 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7875. Min Act: -0.1700

Data Index: 6837078 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8045. Min Act: -0.1700

Data Index: 2892836 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7930. Min Act: -0.1700

Data Index: 1406474 (Open Web Text)

Max Activating Token Index: 396