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

Dataset: Open Web Text

Neuron 2146 in Layer 2

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: 4.0197. Min Range: -4.0197

Max Act: 4.0197. Min Act: -0.1700

Data Index: 7143055 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.0197. Min Range: -4.0197

Max Act: 4.0139. Min Act: -0.1700

Data Index: 4424897 (Open Web Text)

Max Activating Token Index: 748

Text #2

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.8641. Min Act: -0.1700

Data Index: 3891599 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.8449. Min Act: -0.1700

Data Index: 2137166 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.8287. Min Act: -0.1700

Data Index: 1329122 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7862. Min Act: -0.1700

Data Index: 8377424 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7805. Min Act: -0.1700

Data Index: 7815914 (Open Web Text)

Max Activating Token Index: 703

Text #7

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7998. Min Act: -0.1700

Data Index: 2929199 (Open Web Text)

Max Activating Token Index: 315

Text #8

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7612. Min Act: -0.1700

Data Index: 4643291 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7382. Min Act: -0.1700

Data Index: 5789497 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7355. Min Act: -0.1700

Data Index: 804284 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7525. Min Act: -0.1700

Data Index: 8509515 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7089. Min Act: -0.1700

Data Index: 2592494 (Open Web Text)

Max Activating Token Index: 390

Text #13

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7126. Min Act: -0.1700

Data Index: 187237 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.7147. Min Act: -0.1700

Data Index: 1329119 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.6878. Min Act: -0.1700

Data Index: 4933422 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.6570. Min Act: -0.1700

Data Index: 1448203 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.6899. Min Act: -0.1700

Data Index: 5594623 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.6873. Min Act: -0.1700

Data Index: 6983026 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 4.0197. Min Range: -4.0197

Max Act: 3.6560. Min Act: -0.1700

Data Index: 811144 (Open Web Text)

Max Activating Token Index: 993