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

Dataset: Open Web Text

Neuron 2389 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: 3.7368. Min Range: -3.7368

Max Act: 3.7167. Min Act: -0.1700

Data Index: 5154119 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.7368. Min Act: -0.1700

Data Index: 5766149 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6682. Min Act: -0.1700

Data Index: 7137990 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6636. Min Act: -0.1700

Data Index: 7733997 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6599. Min Act: -0.1700

Data Index: 585966 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6500. Min Act: -0.1700

Data Index: 2233247 (Open Web Text)

Max Activating Token Index: 147

Text #6

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6563. Min Act: -0.1700

Data Index: 6795634 (Open Web Text)

Max Activating Token Index: 844

Text #7

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6682. Min Act: -0.1700

Data Index: 8630310 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1815181 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6495. Min Act: -0.1700

Data Index: 8064875 (Open Web Text)

Max Activating Token Index: 440

Text #10

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6586. Min Act: -0.1700

Data Index: 6753092 (Open Web Text)

Max Activating Token Index: 868

Text #11

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6323. Min Act: -0.1700

Data Index: 1961412 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6310. Min Act: -0.1700

Data Index: 4222345 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6413. Min Act: -0.1700

Data Index: 8357224 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6403. Min Act: -0.1700

Data Index: 1158305 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6397. Min Act: -0.1700

Data Index: 2606045 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6297. Min Act: -0.1700

Data Index: 3723203 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6272. Min Act: -0.1700

Data Index: 6116749 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6440. Min Act: -0.1700

Data Index: 6063979 (Open Web Text)

Max Activating Token Index: 273

Text #19

Max Range: 3.7368. Min Range: -3.7368

Max Act: 3.6682. Min Act: -0.1700

Data Index: 3177707 (Open Web Text)

Max Activating Token Index: 387