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

Dataset: Open Web Text

Neuron 1948 in Layer 6

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: 4.5718. Min Range: -4.5718

Max Act: 4.5458. Min Act: -0.1700

Data Index: 3335382 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.5718. Min Act: -0.1700

Data Index: 1103248 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.5224. Min Act: -0.1700

Data Index: 2930642 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4848. Min Act: -0.1700

Data Index: 5594238 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4996. Min Act: -0.1700

Data Index: 5027134 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.5018. Min Act: -0.1700

Data Index: 2306531 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4837. Min Act: -0.1700

Data Index: 4723852 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4179. Min Act: -0.1700

Data Index: 1025250 (Open Web Text)

Max Activating Token Index: 896

Text #8

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4238. Min Act: -0.1700

Data Index: 8320826 (Open Web Text)

Max Activating Token Index: 286

Text #9

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4000. Min Act: -0.1700

Data Index: 7169371 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4214. Min Act: -0.1700

Data Index: 7530293 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.4233. Min Act: -0.1700

Data Index: 5363708 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3875. Min Act: -0.1700

Data Index: 6106057 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3886. Min Act: -0.1700

Data Index: 1347712 (Open Web Text)

Max Activating Token Index: 385

Text #14

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3842. Min Act: -0.1700

Data Index: 2967176 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3809. Min Act: -0.1700

Data Index: 2849724 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3657. Min Act: -0.1700

Data Index: 3612920 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3504. Min Act: -0.1700

Data Index: 5705538 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3281. Min Act: -0.1700

Data Index: 2452032 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 4.5718. Min Range: -4.5718

Max Act: 4.3418. Min Act: -0.1700

Data Index: 5192421 (Open Web Text)

Max Activating Token Index: 910