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

Dataset: Open Web Text

Neuron 1003 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: 3.8657. Min Range: -3.8657

Max Act: 3.8657. Min Act: -0.1700

Data Index: 2307846 (Open Web Text)

Max Activating Token Index: 278

Text #1

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7815. Min Act: -0.1700

Data Index: 6654390 (Open Web Text)

Max Activating Token Index: 209

Text #2

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7042. Min Act: -0.1700

Data Index: 3577003 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6937. Min Act: -0.1700

Data Index: 520814 (Open Web Text)

Max Activating Token Index: 95

Text #4

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6941. Min Act: -0.1700

Data Index: 4148456 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6930. Min Act: -0.1700

Data Index: 7879804 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7149. Min Act: -0.1700

Data Index: 5992357 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6901. Min Act: -0.1700

Data Index: 2720852 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6563. Min Act: -0.1700

Data Index: 108579 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6449. Min Act: -0.1700

Data Index: 6604861 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6721. Min Act: -0.1700

Data Index: 815398 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6178. Min Act: -0.1700

Data Index: 8747103 (Open Web Text)

Max Activating Token Index: 228

Text #12

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6472. Min Act: -0.1700

Data Index: 3505926 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6283. Min Act: -0.1700

Data Index: 8395836 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6190. Min Act: -0.1700

Data Index: 7892247 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1286280 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6247. Min Act: -0.1700

Data Index: 7759429 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6311. Min Act: -0.1700

Data Index: 1224250 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6448. Min Act: -0.1700

Data Index: 5329886 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6208. Min Act: -0.1700

Data Index: 2834668 (Open Web Text)

Max Activating Token Index: 970