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

Dataset: Open Web Text

Neuron 1212 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: 3.7429. Min Range: -3.7429

Max Act: 3.7410. Min Act: -0.1700

Data Index: 1180189 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.7429. Min Act: -0.1700

Data Index: 2012387 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.7341. Min Act: -0.1700

Data Index: 7264599 (Open Web Text)

Max Activating Token Index: 975

Text #3

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.6972. Min Act: -0.1700

Data Index: 1221053 (Open Web Text)

Max Activating Token Index: 191

Text #4

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.6276. Min Act: -0.1700

Data Index: 4109531 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.5904. Min Act: -0.1700

Data Index: 8536703 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.6207. Min Act: -0.1700

Data Index: 6375842 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.5711. Min Act: -0.1700

Data Index: 5004112 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.5312. Min Act: -0.1700

Data Index: 3828836 (Open Web Text)

Max Activating Token Index: 230

Text #9

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4453. Min Act: -0.1700

Data Index: 8290687 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.5051. Min Act: -0.1700

Data Index: 1693872 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4714. Min Act: -0.1700

Data Index: 8439415 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1994937 (Open Web Text)

Max Activating Token Index: 798

Text #13

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4610. Min Act: -0.1700

Data Index: 4375144 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4695. Min Act: -0.1700

Data Index: 3437213 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4813. Min Act: -0.1700

Data Index: 6468205 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4830. Min Act: -0.1700

Data Index: 938255 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4424. Min Act: -0.1700

Data Index: 5577672 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4351. Min Act: -0.1700

Data Index: 1517912 (Open Web Text)

Max Activating Token Index: 592

Text #19

Max Range: 3.7429. Min Range: -3.7429

Max Act: 3.4085. Min Act: -0.1700

Data Index: 2471108 (Open Web Text)

Max Activating Token Index: 40