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

Dataset: Open Web Text

Neuron 1564 in Layer 4

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: 3.8268. Min Range: -3.8268

Max Act: 3.8268. Min Act: -0.1700

Data Index: 5969682 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.8122. Min Act: -0.1700

Data Index: 4586323 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7683. Min Act: -0.1700

Data Index: 6610130 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7499. Min Act: -0.1700

Data Index: 5554488 (Open Web Text)

Max Activating Token Index: 819

Text #4

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7477. Min Act: -0.1700

Data Index: 5454453 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7569. Min Act: -0.1700

Data Index: 3148189 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7613. Min Act: -0.1700

Data Index: 308927 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7063. Min Act: -0.1700

Data Index: 4639317 (Open Web Text)

Max Activating Token Index: 217

Text #8

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7154. Min Act: -0.1700

Data Index: 5159767 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7019. Min Act: -0.1700

Data Index: 7336049 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6956. Min Act: -0.1700

Data Index: 4548286 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6681. Min Act: -0.1700

Data Index: 2047594 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6485. Min Act: -0.1700

Data Index: 7025948 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6339. Min Act: -0.1700

Data Index: 633964 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6171. Min Act: -0.1700

Data Index: 6141539 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6360. Min Act: -0.1700

Data Index: 147556 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6239. Min Act: -0.1700

Data Index: 6246396 (Open Web Text)

Max Activating Token Index: 852

Text #17

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6098. Min Act: -0.1700

Data Index: 4734875 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6575. Min Act: -0.1700

Data Index: 3862453 (Open Web Text)

Max Activating Token Index: 279

Text #19

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6322. Min Act: -0.1700

Data Index: 5094036 (Open Web Text)

Max Activating Token Index: 328